[Docs] Update links (#738)
* update links to main branch * update mmdet and mmseg * update readthedocs links1.x
Yixiao Fang
GitHub
parent
46f2a6c5b3
commit
66c795ada1
94
README.md
94
README.md
|
|
@ -19,16 +19,16 @@
|
|||
<div> </div>
|
||||
|
||||
[](https://pypi.org/project/mmselfsup)
|
||||
[](https://mmselfsup.readthedocs.io/en/dev-1.x/)
|
||||
[](https://mmselfsup.readthedocs.io/en/latest/)
|
||||
[](https://github.com/open-mmlab/mmselfsup/actions)
|
||||
[](https://codecov.io/gh/open-mmlab/mmselfsup)
|
||||
[](https://github.com/open-mmlab/mmselfsup/blob/master/LICENSE)
|
||||
[](https://github.com/open-mmlab/mmselfsup/blob/main/LICENSE)
|
||||
[](https://github.com/open-mmlab/mmselfsup/issues)
|
||||
|
||||
[📘Documentation](https://mmselfsup.readthedocs.io/en/dev-1.x/) |
|
||||
[🛠️Installation](https://mmselfsup.readthedocs.io/en/dev-1.x/get_started.html) |
|
||||
[👀Model Zoo](https://mmselfsup.readthedocs.io/en/dev-1.x/model_zoo.html) |
|
||||
[🆕Update News](https://mmselfsup.readthedocs.io/en/dev-1.x/notes/changelog.html) |
|
||||
[📘Documentation](https://mmselfsup.readthedocs.io/en/latest/) |
|
||||
[🛠️Installation](https://mmselfsup.readthedocs.io/en/latest/get_started.html) |
|
||||
[👀Model Zoo](https://mmselfsup.readthedocs.io/en/latest/model_zoo.html) |
|
||||
[🆕Update News](https://mmselfsup.readthedocs.io/en/latest/notes/changelog.html) |
|
||||
[🤔Reporting Issues](https://github.com/open-mmlab/mmselfsup/issues/new/choose)
|
||||
|
||||
🌟 MMSelfSup will be integrated into MMPreTrain， which is a newly upgraded open-source framework for visual pre-training. It has set out to provide multiple powerful pre-trained backbones and support different pre-training strategies.
|
||||
|
|
@ -89,7 +89,7 @@ The master branch works with **PyTorch 1.6** or higher.
|
|||
|
||||
## What's New
|
||||
|
||||
**The default branch has been switched to `1.x` from `master`, and we encourage users to migrate to the latest version, though it comes with some cost. Please refer to [Migration Guide](https://mmselfsup.readthedocs.io/en/1.x/migration.html) for more details.**
|
||||
**The default branch has been switched to `1.x` from `master`, and we encourage users to migrate to the latest version, though it comes with some cost. Please refer to [Migration Guide](https://mmselfsup.readthedocs.io/en/latest/migration.html) for more details.**
|
||||
|
||||
MMSelfSup **v1.0.0rc6** was released in 10/02/2023.
|
||||
|
||||
|
|
@ -103,71 +103,71 @@ MMSelfSup **v1.0.0rc5** was released in 30/12/2022.
|
|||
- Add Solution of FGIA ACCV 2022 (1st Place)
|
||||
- Refactor t-SNE
|
||||
|
||||
Please refer to [Changelog](https://mmselfsup.readthedocs.io/en/dev-1.x/notes/changelog.html) for details and release history.
|
||||
Please refer to [Changelog](https://mmselfsup.readthedocs.io/en/latest/notes/changelog.html) for details and release history.
|
||||
|
||||
Differences between MMSelfSup 1.x and 0.x can be found in [Migration](https://mmselfsup.readthedocs.io/en/dev-1.x/migration.html).
|
||||
Differences between MMSelfSup 1.x and 0.x can be found in [Migration](https://mmselfsup.readthedocs.io/en/latest/migration.html).
|
||||
|
||||
## Installation
|
||||
|
||||
MMSelfSup depends on [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open-mmlab/mmcv), [MMEngine](https://github.com/open-mmlab/mmengine) and [MMClassification](https://github.com/open-mmlab/mmclassification).
|
||||
|
||||
Please refer to [Installation](https://mmselfsup.readthedocs.io/en/dev-1.x/get_started.html) for more detailed instruction.
|
||||
Please refer to [Installation](https://mmselfsup.readthedocs.io/en/latest/get_started.html) for more detailed instruction.
|
||||
|
||||
## Get Started
|
||||
|
||||
For tutorials, we provide [User Guides](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/index.html) for basic usage:
|
||||
For tutorials, we provide [User Guides](https://mmselfsup.readthedocs.io/en/latest/user_guides/index.html) for basic usage:
|
||||
|
||||
Pretrain
|
||||
|
||||
- [Config](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/1_config.html)
|
||||
- [Prepare Dataset](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/2_dataset_prepare.html)
|
||||
- [Pretrain with Existing Models](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/3_pretrain.html)
|
||||
- [Config](https://mmselfsup.readthedocs.io/en/latest/user_guides/1_config.html)
|
||||
- [Prepare Dataset](https://mmselfsup.readthedocs.io/en/latest/user_guides/2_dataset_prepare.html)
|
||||
- [Pretrain with Existing Models](https://mmselfsup.readthedocs.io/en/latest/user_guides/3_pretrain.html)
|
||||
|
||||
Downetream Tasks
|
||||
|
||||
- [Classification](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/classification.html)
|
||||
- [Detection](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/detection.html)
|
||||
- [Segmentation](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/segmentation.html)
|
||||
- [Classification](https://mmselfsup.readthedocs.io/en/latest/user_guides/classification.html)
|
||||
- [Detection](https://mmselfsup.readthedocs.io/en/latest/user_guides/detection.html)
|
||||
- [Segmentation](https://mmselfsup.readthedocs.io/en/latest/user_guides/segmentation.html)
|
||||
|
||||
Useful Tools
|
||||
|
||||
- [Visualization](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/visualization.html)
|
||||
- [Analysis Tools](https://mmselfsup.readthedocs.io/en/dev-1.x/user_guides/analysis_tools.html)
|
||||
- [Visualization](https://mmselfsup.readthedocs.io/en/latest/user_guides/visualization.html)
|
||||
- [Analysis Tools](https://mmselfsup.readthedocs.io/en/latest/user_guides/analysis_tools.html)
|
||||
|
||||
[Advanced Guides](https://mmselfsup.readthedocs.io/en/dev-1.x/advanced_guides/index.html) and [Colab Tutorials](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/demo/mmselfsup_colab_tutorial.ipynb) are also provided.
|
||||
[Advanced Guides](https://mmselfsup.readthedocs.io/en/latest/advanced_guides/index.html) and [Colab Tutorials](https://github.com/open-mmlab/mmselfsup/blob/main/demo/mmselfsup_colab_tutorial.ipynb) are also provided.
|
||||
|
||||
Please refer to [FAQ](https://mmselfsup.readthedocs.io/en/dev-1.x/notes/faq.html) for frequently asked questions.
|
||||
Please refer to [FAQ](https://mmselfsup.readthedocs.io/en/latest/notes/faq.html) for frequently asked questions.
|
||||
|
||||
## Model Zoo
|
||||
|
||||
Please refer to [Model Zoo.md](https://mmselfsup.readthedocs.io/en/dev-1.x/model_zoo.html) for a comprehensive set of pre-trained models and benchmarks.
|
||||
Please refer to [Model Zoo.md](https://mmselfsup.readthedocs.io/en/latest/model_zoo.html) for a comprehensive set of pre-trained models and benchmarks.
|
||||
|
||||
Supported algorithms:
|
||||
|
||||
- [x] [Relative Location (ICCV'2015)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/relavive_loc)
|
||||
- [x] [Rotation Prediction (ICLR'2018)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/rotation_pred)
|
||||
- [x] [DeepCluster (ECCV'2018)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/deepcluster)
|
||||
- [x] [NPID (CVPR'2018)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/npid)
|
||||
- [x] [ODC (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/odc)
|
||||
- [x] [MoCo v1 (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mocov1)
|
||||
- [x] [SimCLR (ICML'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/simclr)
|
||||
- [x] [MoCo v2 (arXiv'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mocov2)
|
||||
- [x] [BYOL (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/byol)
|
||||
- [x] [SwAV (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/swav)
|
||||
- [x] [DenseCL (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/densecl)
|
||||
- [x] [SimSiam (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/simsiam)
|
||||
- [x] [Barlow Twins (ICML'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/barlowtwins)
|
||||
- [x] [MoCo v3 (ICCV'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mocov3)
|
||||
- [x] [BEiT (ICLR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/beit)
|
||||
- [x] [MAE (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mae)
|
||||
- [x] [SimMIM (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/simmim)
|
||||
- [x] [MaskFeat (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/maskfeat)
|
||||
- [x] [CAE (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/cae)
|
||||
- [x] [MILAN (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/milan)
|
||||
- [x] [BEiT v2 (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/beitv2)
|
||||
- [x] [EVA (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/eva)
|
||||
- [x] [MixMIM (ArXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mixmim)
|
||||
- [x] [PixMIM (ArXiv'2023)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/pixmim)
|
||||
- [x] [Relative Location (ICCV'2015)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/relavive_loc)
|
||||
- [x] [Rotation Prediction (ICLR'2018)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/rotation_pred)
|
||||
- [x] [DeepCluster (ECCV'2018)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/deepcluster)
|
||||
- [x] [NPID (CVPR'2018)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/npid)
|
||||
- [x] [ODC (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/odc)
|
||||
- [x] [MoCo v1 (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mocov1)
|
||||
- [x] [SimCLR (ICML'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/simclr)
|
||||
- [x] [MoCo v2 (arXiv'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mocov2)
|
||||
- [x] [BYOL (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/byol)
|
||||
- [x] [SwAV (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/swav)
|
||||
- [x] [DenseCL (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/densecl)
|
||||
- [x] [SimSiam (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/simsiam)
|
||||
- [x] [Barlow Twins (ICML'2021)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/barlowtwins)
|
||||
- [x] [MoCo v3 (ICCV'2021)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mocov3)
|
||||
- [x] [BEiT (ICLR'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/beit)
|
||||
- [x] [MAE (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mae)
|
||||
- [x] [SimMIM (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/simmim)
|
||||
- [x] [MaskFeat (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/maskfeat)
|
||||
- [x] [CAE (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/cae)
|
||||
- [x] [MILAN (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/milan)
|
||||
- [x] [BEiT v2 (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/beitv2)
|
||||
- [x] [EVA (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/eva)
|
||||
- [x] [MixMIM (ArXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mixmim)
|
||||
- [x] [PixMIM (ArXiv'2023)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/pixmim)
|
||||
|
||||
More algorithms are in our plan.
|
||||
|
||||
|
|
@ -189,7 +189,7 @@ More algorithms are in our plan.
|
|||
|
||||
## Contributing
|
||||
|
||||
We appreciate all contributions improving MMSelfSup. Please refer to [Contribution Guides](https://mmselfsup.readthedocs.io/en/dev-1.x/notes/contribution_guide.html) for more details about the contributing guideline.
|
||||
We appreciate all contributions improving MMSelfSup. Please refer to [Contribution Guides](https://mmselfsup.readthedocs.io/en/latest/notes/contribution_guide.html) for more details about the contributing guideline.
|
||||
|
||||
## Acknowledgement
|
||||
|
||||
|
|
|
|||
|
|
@ -22,13 +22,13 @@
|
|||
[](https://mmselfsup.readthedocs.io/en/dev-1.x/)
|
||||
[](https://github.com/open-mmlab/mmselfsup/actions)
|
||||
[](https://codecov.io/gh/open-mmlab/mmselfsup)
|
||||
[](https://github.com/open-mmlab/mmselfsup/blob/master/LICENSE)
|
||||
[](https://github.com/open-mmlab/mmselfsup/blob/main/LICENSE)
|
||||
[](https://github.com/open-mmlab/mmselfsup/issues)
|
||||
|
||||
[📘使用文档](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/) |
|
||||
[🛠️安装教程](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/get_started.html) |
|
||||
[👀模型库](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/model_zoo.html) |
|
||||
[🆕更新日志](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/notes/changelog.html) |
|
||||
[📘使用文档](https://mmselfsup.readthedocs.io/zh_CN/latest/) |
|
||||
[🛠️安装教程](https://mmselfsup.readthedocs.io/zh_CN/latest/get_started.html) |
|
||||
[👀模型库](https://mmselfsup.readthedocs.io/zh_CN/latest/model_zoo.html) |
|
||||
[🆕更新日志](https://mmselfsup.readthedocs.io/zh_CN/latest/notes/changelog.html) |
|
||||
[🤔报告问题](https://github.com/open-mmlab/mmselfsup/issues/new/choose)
|
||||
|
||||
🌟 MMSelfSup 将整合进 MMPreTrain，一个全新升级的预训练开源算法框架。
|
||||
|
|
@ -107,71 +107,71 @@ MMSelfSup 是一个基于 PyTorch 实现的开源自监督表征学习工具箱
|
|||
- 添加 FGIA ACCV 2022 比赛第一名方案
|
||||
- 重构了 `t-SNE`
|
||||
|
||||
请参考 [更新日志](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/notes/changelog.html) 获取更多细节和历史版本信息。
|
||||
请参考 [更新日志](https://mmselfsup.readthedocs.io/zh_CN/latest/notes/changelog.html) 获取更多细节和历史版本信息。
|
||||
|
||||
MMSelfSup 1.x 和 0.x 的不同点写在 [迁移文档](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/migration.html) 中。
|
||||
MMSelfSup 1.x 和 0.x 的不同点写在 [迁移文档](https://mmselfsup.readthedocs.io/zh_CN/latest/migration.html) 中。
|
||||
|
||||
## 安装
|
||||
|
||||
MMSelfSup 依赖 [PyTorch](https://pytorch.org/), [MMCV](https://github.com/open-mmlab/mmcv), [MMEngine](https://github.com/open-mmlab/mmengine) 和 [MMClassification](https://github.com/open-mmlab/mmclassification)。
|
||||
|
||||
请参考 [安装文档](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/get_started.html) 获取更详细的安装指南。
|
||||
请参考 [安装文档](https://mmselfsup.readthedocs.io/zh_CN/latest/get_started.html) 获取更详细的安装指南。
|
||||
|
||||
## 快速入门
|
||||
|
||||
我们针对基础使用和进阶用法提供了 [用户指引](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/index.html)：
|
||||
我们针对基础使用和进阶用法提供了 [用户指引](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/index.html)：
|
||||
|
||||
Pretrain
|
||||
|
||||
- [Config](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/1_config.html)
|
||||
- [Prepare Dataset](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/2_dataset_prepare.html)
|
||||
- [Pretrain with Existing Models](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/3_pretrain.html)
|
||||
- [Config](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/1_config.html)
|
||||
- [Prepare Dataset](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/2_dataset_prepare.html)
|
||||
- [Pretrain with Existing Models](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/3_pretrain.html)
|
||||
|
||||
Downetream Tasks
|
||||
|
||||
- [Classification](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/classification.html)
|
||||
- [Detection](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/detection.html)
|
||||
- [Segmentation](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/segmentation.html)
|
||||
- [Classification](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/classification.html)
|
||||
- [Detection](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/detection.html)
|
||||
- [Segmentation](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/segmentation.html)
|
||||
|
||||
Useful Tools
|
||||
|
||||
- [Visualization](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/visualization.html)
|
||||
- [Analysis Tools](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/user_guides/analysis_tools.html)
|
||||
- [Visualization](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/visualization.html)
|
||||
- [Analysis Tools](https://mmselfsup.readthedocs.io/zh_CN/latest/user_guides/analysis_tools.html)
|
||||
|
||||
我们也提供了 [进阶指引](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/advanced_guides/index.html) 和 [Colab 教程](https://github.com/open-mmlab/mmselfsup/blob/master/demo/mmselfsup_colab_tutorial.ipynb)。
|
||||
我们也提供了 [进阶指引](https://mmselfsup.readthedocs.io/zh_CN/latest/advanced_guides/index.html) 和 [Colab 教程](https://github.com/open-mmlab/mmselfsup/blob/main/demo/mmselfsup_colab_tutorial.ipynb)。
|
||||
|
||||
如果遇到问题，请参考 [常见问题解答](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/notes/faq.html)。
|
||||
如果遇到问题，请参考 [常见问题解答](https://mmselfsup.readthedocs.io/zh_CN/latest/notes/faq.html)。
|
||||
|
||||
## 模型库
|
||||
|
||||
请参考 [模型库](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/model_zoo.html) 查看我们更加全面的模型基准结果。
|
||||
请参考 [模型库](https://mmselfsup.readthedocs.io/zh_CN/latest/model_zoo.html) 查看我们更加全面的模型基准结果。
|
||||
|
||||
目前已支持的算法:
|
||||
|
||||
- [x] [Relative Location (ICCV'2015)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/relavive_loc)
|
||||
- [x] [Rotation Prediction (ICLR'2018)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/rotation_pred)
|
||||
- [x] [DeepCluster (ECCV'2018)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/deepcluster)
|
||||
- [x] [NPID (CVPR'2018)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/npid)
|
||||
- [x] [ODC (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/odc)
|
||||
- [x] [MoCo v1 (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mocov1)
|
||||
- [x] [SimCLR (ICML'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/simclr)
|
||||
- [x] [MoCo v2 (arXiv'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mocov2)
|
||||
- [x] [BYOL (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/byol)
|
||||
- [x] [SwAV (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/swav)
|
||||
- [x] [DenseCL (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/densecl)
|
||||
- [x] [SimSiam (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/simsiam)
|
||||
- [x] [Barlow Twins (ICML'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/barlowtwins)
|
||||
- [x] [MoCo v3 (ICCV'2021)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mocov3)
|
||||
- [x] [BEiT (ICLR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/beit)
|
||||
- [x] [MAE (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mae)
|
||||
- [x] [SimMIM (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/simmim)
|
||||
- [x] [MaskFeat (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/maskfeat)
|
||||
- [x] [CAE (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/cae)
|
||||
- [x] [MILAN (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/milan)
|
||||
- [x] [BEiT v2 (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/beitv2)
|
||||
- [x] [EVA (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/eva)
|
||||
- [x] [MixMIM (ArXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/mixmim)
|
||||
- [x] [PixMIM (ArXiv'2023)](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/configs/selfsup/pixmim)
|
||||
- [x] [Relative Location (ICCV'2015)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/relavive_loc)
|
||||
- [x] [Rotation Prediction (ICLR'2018)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/rotation_pred)
|
||||
- [x] [DeepCluster (ECCV'2018)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/deepcluster)
|
||||
- [x] [NPID (CVPR'2018)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/npid)
|
||||
- [x] [ODC (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/odc)
|
||||
- [x] [MoCo v1 (CVPR'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mocov1)
|
||||
- [x] [SimCLR (ICML'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/simclr)
|
||||
- [x] [MoCo v2 (arXiv'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mocov2)
|
||||
- [x] [BYOL (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/byol)
|
||||
- [x] [SwAV (NeurIPS'2020)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/swav)
|
||||
- [x] [DenseCL (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/densecl)
|
||||
- [x] [SimSiam (CVPR'2021)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/simsiam)
|
||||
- [x] [Barlow Twins (ICML'2021)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/barlowtwins)
|
||||
- [x] [MoCo v3 (ICCV'2021)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mocov3)
|
||||
- [x] [BEiT (ICLR'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/beit)
|
||||
- [x] [MAE (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mae)
|
||||
- [x] [SimMIM (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/simmim)
|
||||
- [x] [MaskFeat (CVPR'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/maskfeat)
|
||||
- [x] [CAE (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/cae)
|
||||
- [x] [MILAN (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/milan)
|
||||
- [x] [BEiT v2 (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/beitv2)
|
||||
- [x] [EVA (arXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/eva)
|
||||
- [x] [MixMIM (ArXiv'2022)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/mixmim)
|
||||
- [x] [PixMIM (ArXiv'2023)](https://github.com/open-mmlab/mmselfsup/tree/main/configs/selfsup/pixmim)
|
||||
|
||||
更多的算法实现已经在我们的计划中。
|
||||
|
||||
|
|
@ -193,7 +193,7 @@ Useful Tools
|
|||
|
||||
## 参与贡献
|
||||
|
||||
我们非常欢迎任何有助于提升 MMSelfSup 的贡献，请参考 [贡献指南](https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/notes/contribution_guide.html) 来了解如何参与贡献。
|
||||
我们非常欢迎任何有助于提升 MMSelfSup 的贡献，请参考 [贡献指南](https://mmselfsup.readthedocs.io/zh_CN/latest/notes/contribution_guide.html) 来了解如何参与贡献。
|
||||
|
||||
## 致谢
|
||||
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
_base_ = 'mmdet::mask_rcnn/mask-rcnn_r50-caffe-c4_1x_coco.py'
|
||||
# https://github.com/open-mmlab/mmdetection/blob/dev-3.x/configs/mask_rcnn/mask-rcnn_r50-caffe-c4_1x_coco.py
|
||||
# https://github.com/open-mmlab/mmdetection/blob/main/configs/mask_rcnn/mask-rcnn_r50-caffe-c4_1x_coco.py
|
||||
|
||||
data_preprocessor = dict(
|
||||
type='DetDataPreprocessor',
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
_base_ = 'mmdet::mask_rcnn/mask-rcnn_r50-caffe-c4_1x_coco.py'
|
||||
# https://github.com/open-mmlab/mmdetection/blob/dev-3.x/configs/mask_rcnn/mask-rcnn_r50-caffe-c4_1x_coco.py
|
||||
# https://github.com/open-mmlab/mmdetection/blob/main/configs/mask_rcnn/mask-rcnn_r50-caffe-c4_1x_coco.py
|
||||
|
||||
data_preprocessor = dict(
|
||||
type='DetDataPreprocessor',
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
_base_ = 'mmdet::mask_rcnn/mask-rcnn_r50_fpn_1x_coco.py'
|
||||
# https://github.com/open-mmlab/mmdetection/blob/dev-3.x/configs/mask_rcnn/mask-rcnn_r50_fpn_1x_coco.py
|
||||
# https://github.com/open-mmlab/mmdetection/blob/main/configs/mask_rcnn/mask-rcnn_r50_fpn_1x_coco.py
|
||||
|
||||
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
||||
model = dict(
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
_base_ = 'mmdet::mask_rcnn/mask-rcnn_r50_fpn_1x_coco.py'
|
||||
# https://github.com/open-mmlab/mmdetection/blob/dev-3.x/configs/mask_rcnn/mask-rcnn_r50_fpn_1x_coco.py
|
||||
# https://github.com/open-mmlab/mmdetection/blob/main/configs/mask_rcnn/mask-rcnn_r50_fpn_1x_coco.py
|
||||
|
||||
norm_cfg = dict(type='SyncBN', requires_grad=True)
|
||||
model = dict(
|
||||
|
|
|
|||
|
|
@ -1,5 +1,5 @@
|
|||
_base_ = 'mmdet::pascal_voc/faster-rcnn_r50-caffe-c4_ms-18k_voc0712.py'
|
||||
# https://github.com/open-mmlab/mmdetection/blob/dev-3.x/configs/pascal_voc/faster-rcnn_r50-caffe-c4_ms-18k_voc0712.py
|
||||
# https://github.com/open-mmlab/mmdetection/blob/main/configs/pascal_voc/faster-rcnn_r50-caffe-c4_ms-18k_voc0712.py
|
||||
|
||||
data_preprocessor = dict(
|
||||
type='DetDataPreprocessor',
|
||||
|
|
|
|||
|
|
@ -1,2 +1,2 @@
|
|||
_base_ = 'mmseg::fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py'
|
||||
# https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py
|
||||
# https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb2-40k_cityscapes-769x769.py
|
||||
|
|
|
|||
|
|
@ -1,2 +1,2 @@
|
|||
_base_ = 'mmseg::fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py'
|
||||
# https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py
|
||||
# https://github.com/open-mmlab/mmsegmentation/blob/main/configs/fcn/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py
|
||||
|
|
|
|||
|
|
@ -22,11 +22,11 @@ The classification benchmarks includes 1 downstream task datasets, **ImageNet**.
|
|||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-90e.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-90e.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [barlowtwins_resnet50_8xb256-coslr-300e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py) | 15.51 | 33.98 | 45.96 | 61.90 | 71.01 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [barlowtwins_resnet50_8xb256-coslr-300e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py) | 15.51 | 33.98 | 45.96 | 61.90 | 71.01 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -54,8 +54,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>2048</td>
|
||||
<td>71.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220726_033718.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220730_093018.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220726_033718.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220730_093018.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -65,9 +65,9 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [barlowtwins_resnet50_8xb256-coslr-300e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py) | 63.6 | 63.8 | 62.7 | 61.9 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [barlowtwins_resnet50_8xb256-coslr-300e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py) | 63.6 | 63.8 | 62.7 | 61.9 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -41,9 +41,9 @@ Here, we report the results of the model on ImageNet, the details are below:
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.1</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221128-ab79e626.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221123_103802.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221128-ab79e626.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221123_103802.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beit/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221128-0ca393e9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221127_162126.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beit/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221128-0ca393e9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221127_162126.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -43,9 +43,9 @@ Here, we report the results of the model on ImageNet, the details are below:
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>85.0</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221206_012130.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221206_012130.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beitv2/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221211_155017.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beitv2/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221211_155017.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -26,18 +26,18 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | feature5 | 86.31 | 45.37 | 56.83 | 68.47 | 74.12 | 78.30 | 81.53 | 83.56 | 84.73 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | feature5 | 86.31 | 45.37 | 56.83 | 68.47 | 74.12 | 78.30 | 81.53 | 83.56 | 84.73 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 15.16 | 35.26 | 47.77 | 63.10 | 71.21 |
|
||||
| [resnet50_16xb256-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k.py) | 15.41 | 35.15 | 47.77 | 62.59 | 71.85 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 15.16 | 35.26 | 47.77 | 63.10 | 71.21 |
|
||||
| [resnet50_16xb256-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k.py) | 15.41 | 35.15 | 47.77 | 62.59 | 71.85 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -65,8 +65,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>4096</td>
|
||||
<td>71.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220721_150515.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_130251.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220721_150515.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_130251.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -74,21 +74,21 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 21.25 | 36.55 | 43.66 | 50.74 | 53.82 |
|
||||
| [resnet50_8xb32-accum16-coslr-300e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-300e_in1k.py) | 21.18 | 36.68 | 43.42 | 51.04 | 54.06 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 21.25 | 36.55 | 43.66 | 50.74 | 53.82 |
|
||||
| [resnet50_8xb32-accum16-coslr-300e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-300e_in1k.py) | 21.18 | 36.68 | 43.42 | 51.04 | 54.06 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 63.9 | 64.2 | 62.9 | 61.9 |
|
||||
| [resnet50_8xb32-accum16-coslr-300e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-300e_in1k.py) | 66.1 | 66.3 | 65.2 | 64.4 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 63.9 | 64.2 | 62.9 | 61.9 |
|
||||
| [resnet50_8xb32-accum16-coslr-300e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-300e_in1k.py) | 66.1 | 66.3 | 65.2 | 64.4 |
|
||||
|
||||
### Detection
|
||||
|
||||
|
|
@ -96,19 +96,19 @@ The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007
|
|||
|
||||
#### Pascal VOC 2007 + 2012
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
|
||||
| Self-Supervised Config | AP50 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 80.35 |
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 80.35 |
|
||||
|
||||
#### COCO2017
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 40.9 | 61.0 | 44.6 | 36.8 | 58.1 | 39.5 |
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 40.9 | 61.0 | 44.6 | 36.8 | 58.1 | 39.5 |
|
||||
|
||||
### Segmentation
|
||||
|
||||
|
|
@ -116,11 +116,11 @@ The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes**
|
|||
|
||||
#### Pascal VOC 2012 + Aug
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
|
||||
| Self-Supervised Config | mIOU |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 67.16 |
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-accum16-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 67.16 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -22,9 +22,9 @@ Create a new folder `cae_ckpt` under the root directory and download the
|
|||
Here, we report the results of the model, which is pre-trained on ImageNet-1k
|
||||
for 300 epochs, the details are below:
|
||||
|
||||
| Backbone | Pre-train epoch | Fine-tuning Top-1 | Pre-train Config | Fine-tuning Config | Download |
|
||||
| :------: | :-------------: | :---------------: | :-------------------------------------------------------------------------------------------------------------------------------: | :----------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| ViT-B/16 | 300 | 83.2 | [config](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/cae/cae_vit-base-p16_8xb256-fp16-coslr-300e_in1k.py) | [config](https://github.com/open-mmlab/mmselfsup/blob/master/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/cae/cae_vit-base-p16_16xb256-coslr-300e_in1k-224_20220427-4c786349.pth) \| [log](https://download.openmmlab.com/mmselfsup/cae/cae_vit-base-p16_16xb256-coslr-300e_in1k-224_20220427-4c786349.log.json) |
|
||||
| Backbone | Pre-train epoch | Fine-tuning Top-1 | Pre-train Config | Fine-tuning Config | Download |
|
||||
| :------: | :-------------: | :---------------: | :-----------------------------------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: |
|
||||
| ViT-B/16 | 300 | 83.2 | [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/cae/cae_vit-base-p16_8xb256-fp16-coslr-300e_in1k.py) | [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/cae/cae_vit-base-p16_16xb256-coslr-300e_in1k-224_20220427-4c786349.pth) \| [log](https://download.openmmlab.com/mmselfsup/cae/cae_vit-base-p16_16xb256-coslr-300e_in1k-224_20220427-4c786349.log.json) |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -26,27 +26,27 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [sobel_resnet50_8xb64-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | feature5 | 74.26 | 29.37 | 37.99 | 45.85 | 55.57 | 62.48 | 66.15 | 70.00 | 71.37 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [sobel_resnet50_8xb64-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | feature5 | 74.26 | 29.37 | 37.99 | 45.85 | 55.57 | 62.48 | 66.15 | 70.00 | 71.37 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
The **AvgPool** result is obtained from Linear Evaluation with GlobalAveragePooling. Please refer to [resnet50_linear-8xb32-steplr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py) for details of config.
|
||||
The **AvgPool** result is obtained from Linear Evaluation with GlobalAveragePooling. Please refer to [resnet50_linear-8xb32-steplr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | AvgPool |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- | ------- |
|
||||
| [sobel_resnet50_8xb64-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | 12.78 | 30.81 | 43.88 | 57.71 | 51.68 | 46.92 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | AvgPool |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- | ------- |
|
||||
| [sobel_resnet50_8xb64-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | 12.78 | 30.81 | 43.88 | 57.71 | 51.68 | 46.92 |
|
||||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [sobel_resnet50_8xb64-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | 18.80 | 33.93 | 41.44 | 47.22 | 42.61 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [sobel_resnet50_8xb64-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | 18.80 | 33.93 | 41.44 | 47.22 | 42.61 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -26,17 +26,17 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ---- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | feature5 | 82.5 | 42.68 | 50.64 | 61.74 | 68.17 | 72.99 | 76.07 | 79.19 | 80.55 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | ---------- | ---- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | feature5 | 82.5 | 42.68 | 50.64 | 61.74 | 68.17 | 72.99 | 76.07 | 79.19 | 80.55 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 15.86 | 35.47 | 49.46 | 64.06 | 62.95 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 15.86 | 35.47 | 49.46 | 64.06 | 62.95 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -64,8 +64,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>256</td>
|
||||
<td>63.5</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220727_221415.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220730_091650.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220727_221415.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220730_091650.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -73,19 +73,19 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 21.32 | 36.20 | 43.97 | 51.04 | 50.45 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 21.32 | 36.20 | 43.97 | 51.04 | 50.45 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 48.2 | 48.5 | 46.8 | 45.6 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 48.2 | 48.5 | 46.8 | 45.6 |
|
||||
|
||||
### Detection
|
||||
|
||||
|
|
@ -93,19 +93,19 @@ The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007
|
|||
|
||||
#### Pascal VOC 2007 + 2012
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 82.14 |
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 82.14 |
|
||||
|
||||
#### COCO2017
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | | | | | | |
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | | | | | | |
|
||||
|
||||
### Segmentation
|
||||
|
||||
|
|
@ -113,11 +113,11 @@ The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes**
|
|||
|
||||
#### Pascal VOC 2012 + Aug
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 69.47 |
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | 69.47 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -44,9 +44,9 @@ for 400 epochs, the details are below:
|
|||
<td>4096</td>
|
||||
<td>69.02</td>
|
||||
<td>83.72</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221220_113809.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/elfsup/eva/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221222_134137.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/eva/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221221_212618.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221220_113809.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/elfsup/eva/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221222_134137.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/eva/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221221_212618.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -55,9 +55,9 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
<td>4096</td>
|
||||
<td>60.8</td>
|
||||
<td>82.8</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220718_152424.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220720_104514.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220713_140138.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220718_152424.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220720_104514.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220713_140138.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -65,9 +65,9 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
<td>4096</td>
|
||||
<td>62.5</td>
|
||||
<td>83.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220628_200815.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220713_142534.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220708_183134.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220628_200815.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220713_142534.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220708_183134.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -75,9 +75,9 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
<td>4096</td>
|
||||
<td>65.1</td>
|
||||
<td>83.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220718_134405.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k20220721_203941.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220724_232940.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220718_134405.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k20220721_203941.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220724_232940.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -85,9 +85,9 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
<td>4096</td>
|
||||
<td>67.1</td>
|
||||
<td>83.5</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220815_103458.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220724_232557.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220721_202304.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220815_103458.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220724_232557.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220721_202304.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -95,9 +95,9 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
<td>4096</td>
|
||||
<td>70.7</td>
|
||||
<td>85.2</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220726_202204.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220803_101331.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220729_122511.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220726_202204.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220803_101331.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220729_122511.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -105,9 +105,9 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
<td>4096</td>
|
||||
<td>73.7</td>
|
||||
<td>85.4</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220804_104018.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220808_092730.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220730_235819.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220804_104018.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220808_092730.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220730_235819.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -115,9 +115,9 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
<td>4096</td>
|
||||
<td>75.5</td>
|
||||
<td>85.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220806_210725.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220813_155615.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220813_125305.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220806_210725.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220813_155615.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220813_125305.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-huge-FT-224</td>
|
||||
|
|
@ -125,9 +125,9 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
<td>4096</td>
|
||||
<td>/</td>
|
||||
<td>86.9</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220829_114027.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220829_114027.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-huge-FT-448</td>
|
||||
|
|
@ -135,16 +135,16 @@ methods that use only ImageNet-1K data. Transfer performance in downstream tasks
|
|||
<td>4096</td>
|
||||
<td>/</td>
|
||||
<td>87.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220913_113737.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220913_113737.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
## Evaluating MAE on Detection and Segmentation
|
||||
|
||||
If you want to evaluate your model on detection or segmentation task, we provide a [script](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/model_converters/mmcls2timm.py) to convert the model keys from MMClassification style to timm style.
|
||||
If you want to evaluate your model on detection or segmentation task, we provide a [script](https://github.com/open-mmlab/mmselfsup/blob/main/tools/model_converters/mmcls2timm.py) to convert the model keys from MMClassification style to timm style.
|
||||
|
||||
```sh
|
||||
cd $MMSELFSUP
|
||||
|
|
|
|||
|
|
@ -41,9 +41,9 @@ Here, we report the results of the model on ImageNet, the details are below:
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.4</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221019_194256.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221019_194256.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221026_105344.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221026_105344.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -63,9 +63,9 @@ for 400 epochs, the details are below:
|
|||
<td>4096</td>
|
||||
<td>78.9</td>
|
||||
<td>85.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221123_112721.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> |<a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth'> model </a>| <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221125_031826.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/milan/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan.py'>config</a> |<a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth'> model </a>| <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221125_031826.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221123_112721.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> |<a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth'> model </a>| <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221125_031826.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/milan/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan.py'>config</a> |<a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth'> model </a>| <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221125_031826.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -55,8 +55,8 @@ Here, we report the results of the model on ImageNet, the details are below:
|
|||
<td>300</td>
|
||||
<td>2048</td>
|
||||
<td>84.63</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221204_134711.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mixmim/classification/mixmim-base-p16_ft-8xb128-coslr-100e-in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221206_143046.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221204_134711.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mixmim/classification/mixmim-base-p16_ft-8xb128-coslr-100e-in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221206_143046.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -26,17 +26,17 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | feature5 | 84.04 | 43.14 | 53.29 | 65.34 | 71.03 | 75.42 | 78.48 | 80.88 | 82.23 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | feature5 | 84.04 | 43.14 | 53.29 | 65.34 | 71.03 | 75.42 | 78.48 | 80.88 | 82.23 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 15.96 | 34.22 | 45.78 | 61.11 | 66.24 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 15.96 | 34.22 | 45.78 | 61.11 | 66.24 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -64,8 +64,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>256</td>
|
||||
<td>67.5</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220721_215805.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220724_172046.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220721_215805.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220724_172046.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -73,19 +73,19 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 20.92 | 35.72 | 42.62 | 49.79 | 52.25 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 20.92 | 35.72 | 42.62 | 49.79 | 52.25 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 55.6 | 55.7 | 53.7 | 52.5 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 55.6 | 55.7 | 53.7 | 52.5 |
|
||||
|
||||
### Detection
|
||||
|
||||
|
|
@ -93,19 +93,19 @@ The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007
|
|||
|
||||
#### Pascal VOC 2007 + 2012
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
|
||||
| Self-Supervised Config | AP50 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 81.06 |
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 81.06 |
|
||||
|
||||
#### COCO2017
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 40.2 | 59.7 | 44.2 | 36.1 | 56.7 | 38.8 |
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 40.2 | 59.7 | 44.2 | 36.1 | 56.7 | 38.8 |
|
||||
|
||||
### Segmentation
|
||||
|
||||
|
|
@ -113,11 +113,11 @@ The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes**
|
|||
|
||||
#### Pascal VOC 2012 + Aug
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
|
||||
| Self-Supervised Config | mIOU |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 67.55 |
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | 67.55 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -42,8 +42,8 @@ In this page, we provide benchmarks as much as possible to evaluate our pre-trai
|
|||
<td>4096</td>
|
||||
<td>69.6</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220915_154635.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113350.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220915_154635.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113350.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -52,8 +52,8 @@ In this page, we provide benchmarks as much as possible to evaluate our pre-trai
|
|||
<td>4096</td>
|
||||
<td>72.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220915_180538.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113403.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220915_180538.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113403.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -62,8 +62,8 @@ In this page, we provide benchmarks as much as possible to evaluate our pre-trai
|
|||
<td>4096</td>
|
||||
<td>74.4</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220919_111209.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220926_102021.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220919_111209.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220926_102021.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -72,8 +72,8 @@ In this page, we provide benchmarks as much as possible to evaluate our pre-trai
|
|||
<td>4096</td>
|
||||
<td>73.6</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220721_153833.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-small-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220724_140850.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220721_153833.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-small-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220724_140850.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -82,9 +82,9 @@ In this page, we provide benchmarks as much as possible to evaluate our pre-trai
|
|||
<td>4096</td>
|
||||
<td>76.9</td>
|
||||
<td>83.0</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220725_104223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220729_004628.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb64-coslr-150e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220809_103500.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220725_104223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220729_004628.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb64-coslr-150e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220809_103500.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -92,9 +92,9 @@ In this page, we provide benchmarks as much as possible to evaluate our pre-trai
|
|||
<td>4096</td>
|
||||
<td>/</td>
|
||||
<td>83.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220818_143032.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220818_143032.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb64-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220825_201433.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb64-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220825_201433.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -30,17 +30,17 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | feature5 | 76.75 | 26.96 | 35.37 | 44.48 | 53.89 | 60.39 | 66.41 | 71.48 | 73.39 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | feature5 | 76.75 | 26.96 | 35.37 | 44.48 | 53.89 | 60.39 | 66.41 | 71.48 | 73.39 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 14.68 | 31.98 | 42.85 | 56.95 | 58.41 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 14.68 | 31.98 | 42.85 | 56.95 | 58.41 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -68,8 +68,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>256</td>
|
||||
<td>58.3</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220825-a67c5440.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220725_161221.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-661b736e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220728_150535.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220825-a67c5440.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220725_161221.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-661b736e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220728_150535.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -77,19 +77,19 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 19.98 | 34.86 | 41.59 | 48.43 | 48.71 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 19.98 | 34.86 | 41.59 | 48.43 | 48.71 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 42.9 | 44.0 | 43.2 | 42.2 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 42.9 | 44.0 | 43.2 | 42.2 |
|
||||
|
||||
### Detection
|
||||
|
||||
|
|
@ -97,19 +97,19 @@ The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007
|
|||
|
||||
#### Pascal VOC 2007 + 2012
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 79.52 |
|
||||
| Self-Supervised Config | AP50 |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 79.52 |
|
||||
|
||||
#### COCO2017
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 38.5 | 57.7 | 42.0 | 34.6 | 54.8 | 37.1 |
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 38.5 | 57.7 | 42.0 | 34.6 | 54.8 | 37.1 |
|
||||
|
||||
### Segmentation
|
||||
|
||||
|
|
@ -117,11 +117,11 @@ The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes**
|
|||
|
||||
#### Pascal VOC 2012 + Aug
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 65.45 |
|
||||
| Self-Supervised Config | mIOU |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-steplr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | 65.45 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -26,35 +26,35 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb64-steplr-440e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | feature5 | 78.42 | 32.42 | 40.27 | 49.95 | 59.96 | 65.71 | 69.99 | 73.64 | 75.13 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------ | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb64-steplr-440e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | feature5 | 78.42 | 32.42 | 40.27 | 49.95 | 59.96 | 65.71 | 69.99 | 73.64 | 75.13 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
The **AvgPool** result is obtained from Linear Evaluation with GlobalAveragePooling. Please refer to [resnet50_linear-8xb32-steplr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py) for details of config.
|
||||
The **AvgPool** result is obtained from Linear Evaluation with GlobalAveragePooling. Please refer to [resnet50_linear-8xb32-steplr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | AvgPool |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- | ------- |
|
||||
| [resnet50_8xb64-steplr-440e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | 14.76 | 31.82 | 42.44 | 55.76 | 57.70 | 53.42 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | AvgPool |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------ | -------- | -------- | -------- | -------- | -------- | ------- |
|
||||
| [resnet50_8xb64-steplr-440e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | 14.76 | 31.82 | 42.44 | 55.76 | 57.70 | 53.42 |
|
||||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb64-steplr-440e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | 19.28 | 34.09 | 40.90 | 47.04 | 48.35 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------ | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb64-steplr-440e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | 19.28 | 34.09 | 40.90 | 47.04 | 48.35 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb64-steplr-440e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | 38.5 | 39.1 | 37.8 | 36.9 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------ | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb64-steplr-440e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | 38.5 | 39.1 | 37.8 | 36.9 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -62,9 +62,9 @@ Here, we report the results of the model on ImageNet, the details are below:
|
|||
<td>4096</td>
|
||||
<td>63.3</td>
|
||||
<td>83.1</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.json'> log </a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>PixMIM</td>
|
||||
|
|
@ -73,9 +73,9 @@ Here, we report the results of the model on ImageNet, the details are below:
|
|||
<td>4096</td>
|
||||
<td>67.5</td>
|
||||
<td>83.5</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.json'> log </a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
@ -129,7 +129,7 @@ GPUS=8 bash tools/benchmarks/classification/mim_dist_train.sh configs/selfsup/pi
|
|||
|
||||
## Detection and Segmentation
|
||||
|
||||
If you want to evaluate your model on detection or segmentation task, we provide a [script](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/model_converters/mmcls2timm.py) to convert the model keys from MMClassification style to timm style.
|
||||
If you want to evaluate your model on detection or segmentation task, we provide a [script](https://github.com/open-mmlab/mmselfsup/blob/main/tools/model_converters/mmcls2timm.py) to convert the model keys from MMClassification style to timm style.
|
||||
|
||||
```sh
|
||||
cd $MMSELFSUP
|
||||
|
|
|
|||
|
|
@ -26,17 +26,17 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | feature4 | 65.52 | 20.36 | 23.12 | 30.66 | 37.02 | 42.55 | 50.00 | 55.58 | 59.28 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | feature4 | 65.52 | 20.36 | 23.12 | 30.66 | 37.02 | 42.55 | 50.00 | 55.58 | 59.28 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 15.11 | 30.47 | 42.83 | 51.20 | 40.96 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 15.11 | 30.47 | 42.83 | 51.20 | 40.96 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -64,8 +64,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>512</td>
|
||||
<td>40.4</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220825-daae1b41.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220802_223045.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-c2a0b188.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220804_194226.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220825-daae1b41.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220802_223045.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-c2a0b188.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220804_194226.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -73,19 +73,19 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 20.69 | 34.72 | 43.01 | 45.97 | 41.96 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 20.69 | 34.72 | 43.01 | 45.97 | 41.96 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 14.5 | 15.0 | 15.0 | 14.2 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 14.5 | 15.0 | 15.0 | 14.2 |
|
||||
|
||||
### Detection
|
||||
|
||||
|
|
@ -93,19 +93,19 @@ The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007
|
|||
|
||||
#### Pascal VOC 2007 + 2012
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
|
||||
| Self-Supervised Config | AP50 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 79.70 |
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 79.70 |
|
||||
|
||||
#### COCO2017
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 37.5 | 56.2 | 41.3 | 33.7 | 53.3 | 36.1 |
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 37.5 | 56.2 | 41.3 | 33.7 | 53.3 | 36.1 |
|
||||
|
||||
### Segmentation
|
||||
|
||||
|
|
@ -113,11 +113,11 @@ The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes**
|
|||
|
||||
#### Pascal VOC 2012 + Aug
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
|
||||
| Self-Supervised Config | mIOU |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 63.49 |
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb64-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 63.49 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -26,17 +26,17 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | feature4 | 67.70 | 20.60 | 24.35 | 31.41 | 39.17 | 46.56 | 53.37 | 59.14 | 62.42 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | feature4 | 67.70 | 20.60 | 24.35 | 31.41 | 39.17 | 46.56 | 53.37 | 59.14 | 62.42 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 12.15 | 31.99 | 44.57 | 54.20 | 45.94 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 12.15 | 31.99 | 44.57 | 54.20 | 45.94 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -64,8 +64,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>128</td>
|
||||
<td>47.0</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220825-a8bf5f69.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220805_113136.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-7c6edcb3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220808_143921.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220825-a8bf5f69.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220805_113136.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-7c6edcb3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220808_143921.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -73,19 +73,19 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 18.94 | 34.72 | 44.53 | 46.30 | 44.12 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 18.94 | 34.72 | 44.53 | 46.30 | 44.12 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 11.0 | 11.9 | 12.6 | 12.4 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------ | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 11.0 | 11.9 | 12.6 | 12.4 |
|
||||
|
||||
### Detection
|
||||
|
||||
|
|
@ -93,19 +93,19 @@ The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007
|
|||
|
||||
#### Pascal VOC 2007 + 2012
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 79.67 |
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 79.67 |
|
||||
|
||||
#### COCO2017
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 37.9 | 56.5 | 41.5 | 34.2 | 53.9 | 36.7 |
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 37.9 | 56.5 | 41.5 | 34.2 | 53.9 | 36.7 |
|
||||
|
||||
### Segmentation
|
||||
|
||||
|
|
@ -113,11 +113,11 @@ The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes**
|
|||
|
||||
#### Pascal VOC 2012 + Aug
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 64.31 |
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----- |
|
||||
| [resnet50_8xb16-steplr-70e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 64.31 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -26,18 +26,18 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ---- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | feature5 | 79.98 | 35.02 | 42.79 | 54.87 | 61.91 | 67.38 | 71.88 | 75.56 | 77.4 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ---- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | feature5 | 79.98 | 35.02 | 42.79 | 54.87 | 61.91 | 67.38 | 71.88 | 75.56 | 77.4 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 16.29 | 31.11 | 39.99 | 55.06 | 62.91 |
|
||||
| [resnet50_16xb256-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py) | 15.44 | 31.47 | 41.83 | 59.44 | 66.41 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| -------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 16.29 | 31.11 | 39.99 | 55.06 | 62.91 |
|
||||
| [resnet50_16xb256-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py) | 15.44 | 31.47 | 41.83 | 59.44 | 66.41 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -65,8 +65,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>256</td>
|
||||
<td>62.7</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220825-15f807a4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220721_103223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-9596a505.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_210050.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220825-15f807a4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220721_103223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-9596a505.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_210050.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -75,8 +75,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>4096</td>
|
||||
<td>66.9</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220721_150508.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_172050.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220721_150508.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_172050.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -85,8 +85,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>4096</td>
|
||||
<td>69.2</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220725_112248.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220730_165101.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220725_112248.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220730_165101.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -94,19 +94,19 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 20.60 | 33.62 | 38.86 | 45.25 | 50.91 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 20.60 | 33.62 | 38.86 | 45.25 | 50.91 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 47.8 | 48.4 | 46.7 | 45.2 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 47.8 | 48.4 | 46.7 | 45.2 |
|
||||
|
||||
### Detection
|
||||
|
||||
|
|
@ -114,19 +114,19 @@ The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007
|
|||
|
||||
#### Pascal VOC 2007 + 2012
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
|
||||
| Self-Supervised Config | AP50 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 79.38 |
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 79.38 |
|
||||
|
||||
#### COCO2017
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 38.7 | 58.1 | 42.4 | 34.9 | 55.3 | 37.5 |
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 38.7 | 58.1 | 42.4 | 34.9 | 55.3 | 37.5 |
|
||||
|
||||
### Segmentation
|
||||
|
||||
|
|
@ -134,11 +134,11 @@ The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes**
|
|||
|
||||
#### Pascal VOC 2012 + Aug
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
|
||||
| Self-Supervised Config | mIOU |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 64.03 |
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ---------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 64.03 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -44,9 +44,9 @@ Here, we report the results of the model, and more results will be coming soon.
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>82.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829_001452.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829_001452.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>SimMIM</td>
|
||||
|
|
@ -56,9 +56,9 @@ Here, we report the results of the model, and more results will be coming soon.
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.5</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | model | log</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | model | log</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>SimMIM</td>
|
||||
|
|
@ -68,9 +68,9 @@ Here, we report the results of the model, and more results will be coming soon.
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220906_141645.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220906_141645.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221207_135847.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221207_135847.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>SimMIM</td>
|
||||
|
|
@ -80,9 +80,9 @@ Here, we report the results of the model, and more results will be coming soon.
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>84.8</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220907_203738.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220907_203738.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220914_133331.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220914_133331.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -26,19 +26,19 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | feature5 | 84.64 | 39.65 | 49.86 | 62.48 | 69.50 | 74.48 | 78.31 | 81.06 | 82.56 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | feature5 | 85.20 | 39.85 | 50.44 | 63.73 | 70.93 | 75.74 | 79.42 | 82.02 | 83.44 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | feature5 | 84.64 | 39.65 | 49.86 | 62.48 | 69.50 | 74.48 | 78.31 | 81.06 | 82.56 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | feature5 | 85.20 | 39.85 | 50.44 | 63.73 | 70.93 | 75.74 | 79.42 | 82.02 | 83.44 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 16.27 | 33.77 | 45.80 | 60.83 | 68.21 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 15.57 | 37.21 | 47.28 | 62.21 | 69.85 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 16.27 | 33.77 | 45.80 | 60.83 | 68.21 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 15.57 | 37.21 | 47.28 | 62.21 | 69.85 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -66,8 +66,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>256</td>
|
||||
<td>68.3</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220725_224724.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220804_175115.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220725_224724.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220804_175115.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -76,8 +76,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>256</td>
|
||||
<td>69.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220726_033722.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220802_120717.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220726_033722.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220802_120717.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -85,21 +85,21 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 21.32 | 35.66 | 43.05 | 50.79 | 53.27 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 21.17 | 35.85 | 43.49 | 50.99 | 54.10 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 21.32 | 35.66 | 43.05 | 50.79 | 53.27 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 21.17 | 35.85 | 43.49 | 50.99 | 54.10 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 57.4 | 57.6 | 55.8 | 54.2 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 60.2 | 60.4 | 58.8 | 57.4 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 57.4 | 57.6 | 55.8 | 54.2 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 60.2 | 60.4 | 58.8 | 57.4 |
|
||||
|
||||
### Detection
|
||||
|
||||
|
|
@ -107,21 +107,21 @@ The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007
|
|||
|
||||
#### Pascal VOC 2007 + 2012
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 79.80 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 79.85 |
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | ----- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 79.80 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 79.85 |
|
||||
|
||||
#### COCO2017
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.6 | 57.6 | 42.3 | 34.6 | 54.8 | 36.9 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 38.8 | 58.0 | 42.3 | 34.9 | 55.3 | 37.6 |
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.6 | 57.6 | 42.3 | 34.6 | 54.8 | 36.9 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 38.8 | 58.0 | 42.3 | 34.9 | 55.3 | 37.6 |
|
||||
|
||||
### Segmentation
|
||||
|
||||
|
|
@ -129,12 +129,12 @@ The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes**
|
|||
|
||||
#### Pascal VOC 2012 + Aug
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 48.35 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 46.27 |
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ------------------------------------------------------------------------------------------------------------------------------------------------ | ----- |
|
||||
| [resnet50_8xb32-coslr-100e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 48.35 |
|
||||
| [resnet50_8xb32-coslr-200e](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 46.27 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -26,17 +26,17 @@ The **Best Layer** indicates that the best results are obtained from which layer
|
|||
|
||||
Besides, k=1 to 96 indicates the hyper-parameter of Low-shot SVM.
|
||||
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | feature5 | 87.00 | 44.68 | 55.41 | 67.64 | 73.67 | 78.14 | 81.58 | 83.98 | 85.15 |
|
||||
| Self-Supervised Config | Best Layer | SVM | k=1 | k=2 | k=4 | k=8 | k=16 | k=32 | k=64 | k=96 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- | ----- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | feature5 | 87.00 | 44.68 | 55.41 | 67.64 | 73.67 | 78.14 | 81.58 | 83.98 | 85.15 |
|
||||
|
||||
#### ImageNet Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_linear-8xb32-steplr-90e_in1k](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_mhead_linear-8xb32-steplr-90e_in1k.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 16.98 | 34.96 | 49.26 | 65.98 | 70.74 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 16.98 | 34.96 | 49.26 | 65.98 | 70.74 |
|
||||
|
||||
<table class="docutils">
|
||||
<thead>
|
||||
|
|
@ -64,8 +64,8 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
<td>256</td>
|
||||
<td>70.5</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220728_141003.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220802_145230.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220728_141003.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220802_145230.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
@ -73,19 +73,19 @@ The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map
|
|||
|
||||
#### Places205 Linear Evaluation
|
||||
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/master/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
The **Feature1 - Feature5** don't have the GlobalAveragePooling, the feature map is pooled to the specific dimensions and then follows a Linear layer to do the classification. Please refer to [resnet50_mhead_8xb32-steplr-28e_places205.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/places205/resnet50_mhead_8xb32-steplr-28e_places205.py) for details of config.
|
||||
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 23.33 | 35.45 | 43.13 | 51.98 | 55.09 |
|
||||
| Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 23.33 | 35.45 | 43.13 | 51.98 | 55.09 |
|
||||
|
||||
#### ImageNet Nearest-Neighbor Classification
|
||||
|
||||
The results are obtained from the features after GlobalAveragePooling. Here, k=10 to 200 indicates different number of nearest neighbors.
|
||||
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 60.5 | 60.6 | 59.0 | 57.6 |
|
||||
| Self-Supervised Config | k=10 | k=20 | k=100 | k=200 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ----- | ----- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 60.5 | 60.6 | 59.0 | 57.6 |
|
||||
|
||||
### Detection
|
||||
|
||||
|
|
@ -93,19 +93,19 @@ The detection benchmarks includes 2 downstream task datasets, **Pascal VOC 2007
|
|||
|
||||
#### Pascal VOC 2007 + 2012
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/voc0712/faster-rcnn_r50-c4_ms-24k_voc0712.py) for details.
|
||||
|
||||
| Self-Supervised Config | AP50 |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 77.64 |
|
||||
| Self-Supervised Config | AP50 |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 77.64 |
|
||||
|
||||
#### COCO2017
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmdetection/coco/mask-rcnn_r50_fpn_ms-1x_coco.py) for details.
|
||||
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 40.2 | 60.5 | 43.9 | 36.3 | 57.5 | 38.8 |
|
||||
| Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 40.2 | 60.5 | 43.9 | 36.3 | 57.5 | 38.8 |
|
||||
|
||||
### Segmentation
|
||||
|
||||
|
|
@ -113,11 +113,11 @@ The segmentation benchmarks includes 2 downstream task datasets, **Cityscapes**
|
|||
|
||||
#### Pascal VOC 2012 + Aug
|
||||
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
Please refer to [config](https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_4xb4-20k_voc12aug-512x512.py) for details.
|
||||
|
||||
| Self-Supervised Config | mIOU |
|
||||
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 63.73 |
|
||||
| Self-Supervised Config | mIOU |
|
||||
| --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- |
|
||||
| [resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py) | 63.73 |
|
||||
|
||||
## Citation
|
||||
|
||||
|
|
|
|||
|
|
@ -53,7 +53,7 @@ Here are the steps to create a new transform.
|
|||
|
||||
### Step 1: Creating the transform
|
||||
|
||||
Write a new transform in [processing.py](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/mmselfsup/datasets/transforms/processing.py) and overwrite the `transform` function, which takes a `dict` as input:
|
||||
Write a new transform in [processing.py](https://github.com/open-mmlab/mmselfsup/tree/main/mmselfsup/datasets/transforms/processing.py) and overwrite the `transform` function, which takes a `dict` as input:
|
||||
|
||||
```python
|
||||
@TRANSFORMS.register_module()
|
||||
|
|
@ -70,7 +70,7 @@ class NewTransform(BaseTransform):
|
|||
|
||||
### Step 2: Add NewTransform to \_\_init\_\_py
|
||||
|
||||
Then, add the transform to [\_\_init\_\_.py](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/mmselfsup/datasets/transforms/__init__.py).
|
||||
Then, add the transform to [\_\_init\_\_.py](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/datasets/transforms/__init__.py).
|
||||
|
||||
```python
|
||||
...
|
||||
|
|
|
|||
|
|
@ -56,7 +56,7 @@ The priority determines the execution order of the hooks. Before training, the l
|
|||
|
||||
### Default hooks
|
||||
|
||||
The following common hooks are already reigistered by [default](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/_base_/default_runtime.py#L3), which is implemented through [`register_default_hooks`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L1750) in MMEngine:
|
||||
The following common hooks are already reigistered by [default](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/_base_/default_runtime.py#L3), which is implemented through [`register_default_hooks`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L1750) in MMEngine:
|
||||
|
||||
| Hooks | Usage | Priority |
|
||||
| :-----------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------------------------------: | :---------------: |
|
||||
|
|
|
|||
|
|
@ -85,7 +85,7 @@ But MMSelfSup also implements some custom evaluation functionalities to support
|
|||
|
||||
- [`knn_classifier()`](mmselfsup.evaluation.functional.knn_classifier)
|
||||
|
||||
It compute accuracy of knn classifier predictions, and is used in [KNN evaluation](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/benchmarks/classification/knn_imagenet/test_knn.py#L179).
|
||||
It compute accuracy of knn classifier predictions, and is used in [KNN evaluation](https://github.com/open-mmlab/mmselfsup/blob/main/tools/benchmarks/classification/knn_imagenet/test_knn.py#L179).
|
||||
|
||||
```python
|
||||
...
|
||||
|
|
|
|||
|
|
@ -10,12 +10,12 @@
|
|||
We have introduced how to build a `Pipeline` in [add_transforms](./add_transforms.md). A `Pipeline` contains a series of
|
||||
`transforms`. There are three main categories of `transforms` in MMSelfSup:
|
||||
|
||||
1. Transforms about processing the data. The unique transforms in MMSelfSup are defined in [processing.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/mmselfsup/datasets/transforms/processing.py), e.g. `RandomCrop`, `RandomResizedCrop` and `RandomGaussianBlur`.
|
||||
1. Transforms about processing the data. The unique transforms in MMSelfSup are defined in [processing.py](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/datasets/transforms/processing.py), e.g. `RandomCrop`, `RandomResizedCrop` and `RandomGaussianBlur`.
|
||||
We may also use some transforms from other repositories, e.g. `LoadImageFromFile` from MMCV.
|
||||
|
||||
2. The transform wrapper for multiple views of an image. It is defined in [wrappers.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/mmselfsup/datasets/transforms/wrappers.py).
|
||||
2. The transform wrapper for multiple views of an image. It is defined in [wrappers.py](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/datasets/transforms/wrappers.py).
|
||||
|
||||
3. The transform to pack data into a format compatible with the inputs of the algorithm. It is defined in [formatting.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/mmselfsup/datasets/transforms/formatting.py).
|
||||
3. The transform to pack data into a format compatible with the inputs of the algorithm. It is defined in [formatting.py](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/datasets/transforms/formatting.py).
|
||||
|
||||
In summary, we implement these `transforms` below. The last two transforms will be introduced in detail.
|
||||
|
||||
|
|
@ -69,7 +69,7 @@ pipeline = [
|
|||
```
|
||||
|
||||
This means that there are two pipelines, which contain 2 views and 6 views, respectively.
|
||||
More examples can be found in [imagenet_mocov1.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/_base_/datasets/imagenet_mocov1.py), [imagenet_mocov2.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/_base_/datasets/imagenet_mocov2.py) and [imagenet_swav_mcrop-2-6.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/_base_/datasets/imagenet_swav_mcrop-2-6.py) etc.
|
||||
More examples can be found in [imagenet_mocov1.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/_base_/datasets/imagenet_mocov1.py), [imagenet_mocov2.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/_base_/datasets/imagenet_mocov2.py) and [imagenet_swav_mcrop-2-6.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/_base_/datasets/imagenet_swav_mcrop-2-6.py) etc.
|
||||
|
||||
## Introduction of `PackSelfSupInputs`
|
||||
|
||||
|
|
|
|||
|
|
@ -86,7 +86,7 @@ pip install -v -e .
|
|||
# thus any local modifications made to the code will take effect without reinstallation.
|
||||
```
|
||||
|
||||
Optionally, if you want to [contribute](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/docs/en/notes/contribution_guide.md) to MMSelfSup or experience experimental functions, please checkout to the `dev-1.x` branch:
|
||||
Optionally, if you want to [contribute](https://github.com/open-mmlab/mmselfsup/blob/main/docs/en/notes/contribution_guide.md) to MMSelfSup or experience experimental functions, please checkout to the `dev-1.x` branch:
|
||||
|
||||
```shell
|
||||
git checkout dev-1.x
|
||||
|
|
@ -124,7 +124,7 @@ You can simply install MMDetection and MMSegmentation with the following command
|
|||
pip install 'mmdet>=3.0.0rc0' 'mmsegmentation>=1.0.0rc0'
|
||||
```
|
||||
|
||||
For more details, you can check the installation page of [MMDetection](https://github.com/open-mmlab/mmdetection/blob/dev-3.x/docs/en/get_started.md) and [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/get_started.md).
|
||||
For more details, you can check the installation page of [MMDetection](https://github.com/open-mmlab/mmdetection/blob/main/docs/en/get_started.md) and [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/get_started.md).
|
||||
|
||||
#### CUDA versions
|
||||
|
||||
|
|
@ -204,7 +204,7 @@ Within Jupyter, the exclamation mark `!` is used to call external executables an
|
|||
|
||||
#### Using MMSelfSup with Docker
|
||||
|
||||
We provide a [Dockerfile](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/docker/Dockerfile) to build an image. Ensure that your [docker version](https://docs.docker.com/engine/install/) >=19.03.
|
||||
We provide a [Dockerfile](https://github.com/open-mmlab/mmselfsup/blob/main/docker/Dockerfile) to build an image. Ensure that your [docker version](https://docs.docker.com/engine/install/) >=19.03.
|
||||
|
||||
```shell
|
||||
# build an image with PyTorch 1.10.0, CUDA 11.3, CUDNN 8.
|
||||
|
|
|
|||
|
|
@ -38,8 +38,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>512</td>
|
||||
<td>40.4</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220825-daae1b41.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220802_223045.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-c2a0b188.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220804_194226.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220825-daae1b41.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220802_223045.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-c2a0b188.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220804_194226.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -49,8 +49,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>128</td>
|
||||
<td>47.0</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220825-a8bf5f69.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220805_113136.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-7c6edcb3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220808_143921.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220825-a8bf5f69.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220805_113136.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-7c6edcb3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220808_143921.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -60,8 +60,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>256</td>
|
||||
<td>58.3</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220825-a67c5440.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220725_161221.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-661b736e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220728_150535.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220825-a67c5440.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220725_161221.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-661b736e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220728_150535.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -71,8 +71,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>256</td>
|
||||
<td>62.7</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220825-15f807a4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220721_103223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-9596a505.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_210050.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220825-15f807a4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220721_103223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-9596a505.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_210050.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -81,8 +81,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>66.9</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220721_150508.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_172050.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220721_150508.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_172050.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -91,8 +91,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>69.2</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220725_112248.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220730_165101.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220725_112248.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220730_165101.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -102,8 +102,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>256</td>
|
||||
<td>67.5</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220721_215805.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220724_172046.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220721_215805.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220724_172046.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -113,8 +113,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>71.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220721_150515.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_130251.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220721_150515.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_130251.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -124,8 +124,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>256</td>
|
||||
<td>70.5</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220728_141003.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220802_145230.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220728_141003.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220802_145230.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -135,8 +135,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>256</td>
|
||||
<td>63.5</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220727_221415.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220730_091650.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220727_221415.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220730_091650.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -146,8 +146,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>256</td>
|
||||
<td>68.3</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220725_224724.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220804_175115.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220725_224724.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220804_175115.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -156,8 +156,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>256</td>
|
||||
<td>69.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220726_033722.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220802_120717.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220726_033722.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220802_120717.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -167,8 +167,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>71.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220726_033718.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220730_093018.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220726_033718.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220730_093018.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -178,8 +178,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>69.6</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220915_154635.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113350.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220915_154635.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113350.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -188,8 +188,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>72.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220915_180538.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113403.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220915_180538.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113403.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -198,8 +198,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>74.4</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220919_111209.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220926_102021.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220919_111209.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220926_102021.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -208,8 +208,8 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>73.6</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220721_153833.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-small-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220724_140850.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220721_153833.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-small-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220724_140850.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -218,9 +218,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>76.9</td>
|
||||
<td>83.0</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220725_104223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220729_004628.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb64-coslr-150e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220809_103500.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220725_104223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220729_004628.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb64-coslr-150e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220809_103500.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -228,9 +228,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>/</td>
|
||||
<td>83.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220818_143032.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220818_143032.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb64-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220825_201433.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb64-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220825_201433.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="9">MAE</td>
|
||||
|
|
@ -239,9 +239,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>60.8</td>
|
||||
<td>82.8</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220718_152424.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220720_104514.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220713_140138.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220718_152424.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220720_104514.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220713_140138.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -249,9 +249,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>62.5</td>
|
||||
<td>83.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220628_200815.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220713_142534.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220708_183134.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220628_200815.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220713_142534.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220708_183134.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -259,9 +259,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>65.1</td>
|
||||
<td>83.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220718_134405.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k20220721_203941.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220724_232940.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220718_134405.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k20220721_203941.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220724_232940.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -269,9 +269,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>67.1</td>
|
||||
<td>83.5</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220815_103458.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220724_232557.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220721_202304.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220815_103458.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220724_232557.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220721_202304.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -279,9 +279,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>70.7</td>
|
||||
<td>85.2</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220726_202204.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220803_101331.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220729_122511.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220726_202204.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220803_101331.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220729_122511.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -289,9 +289,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>73.7</td>
|
||||
<td>85.4</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220804_104018.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220808_092730.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220730_235819.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220804_104018.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220808_092730.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220730_235819.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -299,9 +299,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>75.5</td>
|
||||
<td>85.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220806_210725.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220813_155615.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220813_125305.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220806_210725.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220813_155615.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220813_125305.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-huge-FT-224</td>
|
||||
|
|
@ -309,9 +309,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>/</td>
|
||||
<td>86.9</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220829_114027.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220829_114027.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-huge-FT-448</td>
|
||||
|
|
@ -319,9 +319,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>/</td>
|
||||
<td>87.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220913_113737.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220913_113737.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>CAE</td>
|
||||
|
|
@ -330,9 +330,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/cae/cae_vit-base-p16_16xb128-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220825-404a1929.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220615_163141.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/cae/cae_vit-base-p16_16xb128-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220825-404a1929.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220615_163141.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220711_165500.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220711_165500.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="4">SimMIM</td>
|
||||
|
|
@ -341,9 +341,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>82.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829_001452.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829_001452.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Swin-base-FT224</td>
|
||||
|
|
@ -351,9 +351,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.5</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | model | log</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | model | log</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Swin-base-FT224</td>
|
||||
|
|
@ -361,9 +361,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220906_141645.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220906_141645.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221207_135847.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221207_135847.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Swin-large-FT224</td>
|
||||
|
|
@ -371,9 +371,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>84.8</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220907_203738.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220907_203738.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220914_133331.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220914_133331.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MaskFeat</td>
|
||||
|
|
@ -382,9 +382,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.4</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221019_194256.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221019_194256.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221026_105344.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221026_105344.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>BEiT</td>
|
||||
|
|
@ -393,9 +393,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.1</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221128-ab79e626.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221123_103802.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221128-ab79e626.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221123_103802.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beit/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221128-0ca393e9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221127_162126.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beit/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221128-0ca393e9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221127_162126.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MILAN</td>
|
||||
|
|
@ -404,9 +404,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>78.9</td>
|
||||
<td>85.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221123_112721.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221125_031826.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221124_215401.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221123_112721.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221125_031826.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221124_215401.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>BEiT v2</td>
|
||||
|
|
@ -415,9 +415,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>85.0</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221206_012130.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221206_012130.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beitv2/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221211_155017.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beitv2/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221211_155017.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>EVA</td>
|
||||
|
|
@ -426,9 +426,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>69.0</td>
|
||||
<td>83.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221220_113809.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/elfsup/eva/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221222_134137.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/eva/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221221_212618.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221220_113809.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/elfsup/eva/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221222_134137.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/eva/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221221_212618.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MixMIM</td>
|
||||
|
|
@ -437,9 +437,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>84.6</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221204_134711.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221204_134711.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mixmim/classification/mixmim-base-p16_ft-8xb128-coslr-100e-in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221206_143046.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mixmim/classification/mixmim-base-p16_ft-8xb128-coslr-100e-in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221206_143046.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="2">PixMIM</td>
|
||||
|
|
@ -448,9 +448,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>63.3</td>
|
||||
<td>83.1</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.json'> log </a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -458,9 +458,9 @@ ImageNet has multiple versions, but the most commonly used one is ILSVRC 2012. T
|
|||
<td>4096</td>
|
||||
<td>67.5</td>
|
||||
<td>83.5</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.json'> log </a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ Compatible MMEngine, MMCV, MMClassification, MMDetection and MMSegmentation vers
|
|||
|
||||
## DeepCluster on A100 GPU
|
||||
|
||||
Problem: If you want to try [DeepCluster](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/deepcluster/README.md) algorithm on A100 GPU, use the `faiss` installed by pip will raise error, which is mentioned in [here](https://github.com/facebookresearch/faiss/issues/2076).
|
||||
Problem: If you want to try [DeepCluster](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/deepcluster/README.md) algorithm on A100 GPU, use the `faiss` installed by pip will raise error, which is mentioned in [here](https://github.com/facebookresearch/faiss/issues/2076).
|
||||
|
||||
Please install `faiss` by conda like this:
|
||||
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@ from modelindex.load_model_index import load
|
|||
|
||||
MMSELFSUP_ROOT = Path(__file__).absolute().parents[2]
|
||||
PAPERS_ROOT = Path('papers') # Path to save generated paper pages.
|
||||
GITHUB_PREFIX = 'https://github.com/open-mmlab/mmselfsup/blob/1.x/'
|
||||
GITHUB_PREFIX = 'https://github.com/open-mmlab/mmselfsup/blob/main/'
|
||||
MODELZOO_TEMPLATE = """
|
||||
# Model Zoo Statistics
|
||||
|
||||
|
|
|
|||
|
|
@ -1,3 +1,3 @@
|
|||
## <a href='https://mmselfsup.readthedocs.io/en/dev-1.x/'>English</a>
|
||||
## <a href='https://mmselfsup.readthedocs.io/en/latest/'>English</a>
|
||||
|
||||
## <a href='https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/'>简体中文</a>
|
||||
## <a href='https://mmselfsup.readthedocs.io/zh_CN/latest/'>简体中文</a>
|
||||
|
|
|
|||
|
|
@ -81,8 +81,8 @@ bash tools/dataset_converters/prepare_voc07_cls.sh $YOUR_DATA_ROOT
|
|||
|
||||
### Detection
|
||||
|
||||
To prepare COCO, VOC2007 and VOC2012 for detection, you can refer to [mmdetection](https://github.com/open-mmlab/mmdetection/blob/dev-3.x/docs/en/1_exist_data_model.md).
|
||||
To prepare COCO, VOC2007 and VOC2012 for detection, you can refer to [mmdetection](https://github.com/open-mmlab/mmdetection/blob/main/docs/en/1_exist_data_model.md).
|
||||
|
||||
### Segmentation
|
||||
|
||||
To prepare VOC2012AUG and Cityscapes for segmentation, you can refer to [mmsegmentation](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/2_dataset_prepare.md#prepare-datasets)
|
||||
To prepare VOC2012AUG and Cityscapes for segmentation, you can refer to [mmsegmentation](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#prepare-datasets)
|
||||
|
|
|
|||
|
|
@ -85,7 +85,7 @@ NNODES=2 NODE_RANK=1 PORT=${MASTER_PORT} MASTER_ADDR=${MASTER_ADDR} bash tools/d
|
|||
|
||||
Usually it is slow if you do not have high speed networking like InfiniBand.
|
||||
|
||||
If you launch with slurm, the command is the same as that on single machine described above, but you need to refer to [slurm_train.sh](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/slurm_train.sh) to set appropriate parameters and environment variables.
|
||||
If you launch with slurm, the command is the same as that on single machine described above, but you need to refer to [slurm_train.sh](https://github.com/open-mmlab/mmselfsup/blob/main/tools/slurm_train.sh) to set appropriate parameters and environment variables.
|
||||
|
||||
### Launch multiple jobs on a single machine
|
||||
|
||||
|
|
|
|||
|
|
@ -189,7 +189,7 @@ By using the edited config file, you are able to train a self-supervised model w
|
|||
## Train MAE on COCO Dataset
|
||||
|
||||
```{note}
|
||||
You need to install MMDetection to use the `mmdet.CocoDataset` follow this [documentation](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/get_started.md)
|
||||
You need to install MMDetection to use the `mmdet.CocoDataset` follow this [documentation](https://github.com/open-mmlab/mmdetection/blob/main/docs/en/get_started.md)
|
||||
```
|
||||
|
||||
Follow the aforementioned idea, we also present an example of how to train MAE on COCO dataset. The edited file will be like this:
|
||||
|
|
|
|||
|
|
@ -132,7 +132,7 @@ Remarks:
|
|||
- `${SELFSUP_CONFIG}` is the config file of the self-supervised experiment.
|
||||
- `${CHECKPOINT}`: the path of checkpoint model file.
|
||||
- if you want to change GPU numbers, you could add `GPUS_PER_NODE=4 GPUS=4` at the beginning of the command.
|
||||
- `[optional arguments]`: for optional arguments, you can refer to the [script](https://github.com/open-mmlab/mmselfsup/blob/1.x/tools/benchmarks/classification/knn_imagenet/test_knn.py)
|
||||
- `[optional arguments]`: for optional arguments, you can refer to the [script](https://github.com/open-mmlab/mmselfsup/blob/main/tools/benchmarks/classification/knn_imagenet/test_knn.py)
|
||||
|
||||
An example of command
|
||||
|
||||
|
|
|
|||
|
|
@ -49,7 +49,7 @@ def after_train_iter(...):
|
|||
|
||||
(2) Browse dataset
|
||||
|
||||
The function [`add_datasample()`](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/mmselfsup/visualization/selfsup_visualizer.py#L151) is impleted in [`SelfSupVisualizer`](mmselfsup.visualization.SelfSupVisualizer), and it is mainly used in [browse_dataset.py](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/analysis_tools/browse_dataset.py) for browsing dataset. More tutorial is in section [Visualize Datasets](#visualize-datasets)
|
||||
The function [`add_datasample()`](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/visualization/selfsup_visualizer.py#L151) is impleted in [`SelfSupVisualizer`](mmselfsup.visualization.SelfSupVisualizer), and it is mainly used in [browse_dataset.py](https://github.com/open-mmlab/mmselfsup/blob/main/tools/analysis_tools/browse_dataset.py) for browsing dataset. More tutorial is in section [Visualize Datasets](#visualize-datasets)
|
||||
|
||||
## Use Different Storage Backends
|
||||
|
||||
|
|
@ -129,7 +129,7 @@ Arguments:
|
|||
- `CONFIG_FILE`: config file for t-SNE, which listed in the directory `configs/tsne/`
|
||||
- `CKPT_PATH`: the path or link of the model's checkpoint.
|
||||
- `WORK_DIR`: the directory to save the results of visualization.
|
||||
- `[optional arguments]`: for optional arguments, you can refer to [visualize_tsne.py](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/analysis_tools/visualize_tsne.py)
|
||||
- `[optional arguments]`: for optional arguments, you can refer to [visualize_tsne.py](https://github.com/open-mmlab/mmselfsup/blob/main/tools/analysis_tools/visualize_tsne.py)
|
||||
|
||||
An example of command:
|
||||
|
||||
|
|
@ -171,7 +171,7 @@ Arguments:
|
|||
- `CKPT_PATH`: the path of model's checkpoint.
|
||||
- `IMAGE_PATH`: the input image path.
|
||||
- `OUTPUT_PATH`: the output image path, including 4 sub-images.
|
||||
- `[optional arguments]`: for optional arguments, you can refer to [visualize_reconstruction.py](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/analysis_tools/visualize_reconstruction.py)
|
||||
- `[optional arguments]`: for optional arguments, you can refer to [visualize_reconstruction.py](https://github.com/open-mmlab/mmselfsup/blob/main/tools/analysis_tools/visualize_reconstruction.py)
|
||||
|
||||
An example:
|
||||
|
||||
|
|
|
|||
|
|
@ -53,7 +53,7 @@ train_pipeline = [
|
|||
|
||||
### 步骤 1: 创建转换
|
||||
|
||||
在 [processing.py](https://github.com/open-mmlab/mmselfsup/tree/dev-1.x/mmselfsup/datasets/transforms/processing.py) 中编写一个新的转换类, 并在类中覆盖这个 `transform` 函数, 这个函数接收一个 `dict` 的对象, 并返回一个 `dict` 对象
|
||||
在 [processing.py](https://github.com/open-mmlab/mmselfsup/tree/main/mmselfsup/datasets/transforms/processing.py) 中编写一个新的转换类, 并在类中覆盖这个 `transform` 函数, 这个函数接收一个 `dict` 的对象, 并返回一个 `dict` 对象
|
||||
|
||||
```python
|
||||
@TRANSFORMS.register_module()
|
||||
|
|
@ -70,7 +70,7 @@ class NewTransform(BaseTransform):
|
|||
|
||||
### 步骤 2: 将新转换添加到 \_\_init\_\_py
|
||||
|
||||
然后, 将转换添加到 [\_\_init\_\_.py](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/mmselfsup/datasets/transforms/__init__.py) 。
|
||||
然后, 将转换添加到 [\_\_init\_\_.py](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/datasets/transforms/__init__.py) 。
|
||||
|
||||
```python
|
||||
...
|
||||
|
|
|
|||
|
|
@ -56,7 +56,7 @@
|
|||
|
||||
### 默认钩子
|
||||
|
||||
以下常见的钩子由 MMEngine 中的[`register_default_hooks`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L1750) 实现并在 [default](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/_base_/default_runtime.py#L3) 中进行了注册:
|
||||
以下常见的钩子由 MMEngine 中的[`register_default_hooks`](https://github.com/open-mmlab/mmengine/blob/main/mmengine/runner/runner.py#L1750) 实现并在 [default](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/_base_/default_runtime.py#L3) 中进行了注册:
|
||||
|
||||
| Hooks | Usage | Priority |
|
||||
| :-----------------------------------------------------------------------------------------------------------: | :-------------------------------------------------------------------------------------------: | :---------------: |
|
||||
|
|
|
|||
|
|
@ -85,7 +85,7 @@ results = evaluator.offline_evaluate(data, predictions, chunk_size=128)
|
|||
|
||||
- [`knn_classifier()`](mmselfsup.evaluation.functional.knn_classifier)
|
||||
|
||||
用于计算 knn 分类器预测的准确性,并且用于 [KNN evaluation](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/benchmarks/classification/knn_imagenet/test_knn.py#L179).
|
||||
用于计算 knn 分类器预测的准确性,并且用于 [KNN evaluation](https://github.com/open-mmlab/mmselfsup/blob/main/tools/benchmarks/classification/knn_imagenet/test_knn.py#L179).
|
||||
|
||||
```python
|
||||
...
|
||||
|
|
|
|||
|
|
@ -9,11 +9,11 @@
|
|||
|
||||
在 [add_transforms](./add_transforms.md) 中我们介绍了如何构建 `Pipeline` 。 `Pipeline` 里有一系列的数据变换。MMSelfSup 中数据变换主要分为三类：
|
||||
|
||||
1. 处理数据用到的数据变换。[processing.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/mmselfsup/datasets/transforms/processing.py) 中定义了独特的数据变换，比如`RandomCrop`, `RandomResizedCrop` 和 `RandomGaussianBlur`。我们也可以用其它仓库的数据变换，比如 MMCV 中的 `LoadImageFromFile`。
|
||||
1. 处理数据用到的数据变换。[processing.py](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/datasets/transforms/processing.py) 中定义了独特的数据变换，比如`RandomCrop`, `RandomResizedCrop` 和 `RandomGaussianBlur`。我们也可以用其它仓库的数据变换，比如 MMCV 中的 `LoadImageFromFile`。
|
||||
|
||||
2. 不同视角看同一照片的数据变换打包器。这个定义在 [wrappers.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/mmselfsup/datasets/transforms/wrappers.py)。
|
||||
2. 不同视角看同一照片的数据变换打包器。这个定义在 [wrappers.py](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/datasets/transforms/wrappers.py)。
|
||||
|
||||
3. 将数据变换使得数据能输入算法中。这个定义在 [formatting.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/mmselfsup/datasets/transforms/formatting.py)。
|
||||
3. 将数据变换使得数据能输入算法中。这个定义在 [formatting.py](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/datasets/transforms/formatting.py)。
|
||||
|
||||
总的来说，我们用的是如下的这些数据变换。我们将详细讨论最后两种数据变换。
|
||||
|
||||
|
|
@ -65,7 +65,7 @@ pipeline = [
|
|||
]
|
||||
```
|
||||
|
||||
这意味着有两个数据管道，他们分别有两个角度和六个角度。在 [imagenet_mocov1.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/_base_/datasets/imagenet_mocov1.py) 和 [imagenet_mocov2.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/_base_/datasets/imagenet_mocov2.py) 和 [imagenet_swav_mcrop-2-6.py](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/_base_/datasets/imagenet_swav_mcrop-2-6.py) 中有更多例子。
|
||||
这意味着有两个数据管道，他们分别有两个角度和六个角度。在 [imagenet_mocov1.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/_base_/datasets/imagenet_mocov1.py) 和 [imagenet_mocov2.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/_base_/datasets/imagenet_mocov2.py) 和 [imagenet_swav_mcrop-2-6.py](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/_base_/datasets/imagenet_swav_mcrop-2-6.py) 中有更多例子。
|
||||
|
||||
## PackSelfSupInputs 简介
|
||||
|
||||
|
|
|
|||
|
|
@ -86,7 +86,7 @@ pip install -v -e .
|
|||
# 因此，对代码所做的任何本地修改都将生效，无需重新安装。
|
||||
```
|
||||
|
||||
或者，如果您想为 MMSelfSup 做出[贡献](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/docs/zh_cn/notes/contribution_guides.md)或体验其正在实验中的功能，请查看 `dev-1.x` 分支：
|
||||
或者，如果您想为 MMSelfSup 做出[贡献](https://github.com/open-mmlab/mmselfsup/blob/main/docs/zh_cn/notes/contribution_guides.md)或体验其正在实验中的功能，请查看 `dev-1.x` 分支：
|
||||
|
||||
```shell
|
||||
git checkout dev-1.x
|
||||
|
|
@ -124,7 +124,7 @@ print(mmselfsup.__version__)
|
|||
pip install 'mmdet>=3.0.0rc0' 'mmsegmentation>=1.0.0rc0'
|
||||
```
|
||||
|
||||
更多详细信息，您可以查看 [MMDetection](https://github.com/open-mmlab/mmdetection/blob/dev-3.x/docs/zh_cn/get_started.md) 和 [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/zh_cn/get_started.md) 的安装页面。
|
||||
更多详细信息，您可以查看 [MMDetection](https://github.com/open-mmlab/mmdetection/blob/main/docs/zh_cn/get_started.md) 和 [MMSegmentation](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/zh_cn/get_started.md) 的安装页面。
|
||||
|
||||
#### CUDA 版本
|
||||
|
||||
|
|
@ -202,7 +202,7 @@ print(mmselfsup.__version__)
|
|||
|
||||
#### 通过 Docker 使用 MMSelfSup
|
||||
|
||||
我们提供了一个 [Dockerfile](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/docker/Dockerfile) 来构建镜像。请确保您的 [docker 版本](https://docs.docker.com/engine/install/) >=19.03。
|
||||
我们提供了一个 [Dockerfile](https://github.com/open-mmlab/mmselfsup/blob/main/docker/Dockerfile) 来构建镜像。请确保您的 [docker 版本](https://docs.docker.com/engine/install/) >=19.03。
|
||||
|
||||
```shell
|
||||
# 使用 PyTorch 1.10.0、CUDA 11.3、CUDNN 8 构建镜像。
|
||||
|
|
|
|||
|
|
@ -38,8 +38,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>512</td>
|
||||
<td>40.4</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220825-daae1b41.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220802_223045.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-c2a0b188.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220804_194226.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220825-daae1b41.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/relative-loc_resnet50_8xb64-steplr-70e_in1k_20220802_223045.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-c2a0b188.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220804_194226.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -49,8 +49,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>128</td>
|
||||
<td>47.0</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220825-a8bf5f69.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220805_113136.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-7c6edcb3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220808_143921.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220825-a8bf5f69.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20220805_113136.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-7c6edcb3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220808_143921.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -60,8 +60,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>256</td>
|
||||
<td>58.3</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220825-a67c5440.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220725_161221.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-661b736e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220728_150535.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220825-a67c5440.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/npid_resnet50_8xb32-steplr-200e_in1k_20220725_161221.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-661b736e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/npid/npid_resnet50_8xb32-steplr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220728_150535.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -71,8 +71,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>256</td>
|
||||
<td>62.7</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220825-15f807a4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220721_103223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-9596a505.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_210050.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220825-15f807a4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/simclr_resnet50_8xb32-coslr-200e_in1k_20220721_103223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-9596a505.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_210050.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -81,8 +81,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>66.9</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220721_150508.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_172050.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220825-4d9cce50.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/simclr_resnet50_16xb256-coslr-200e_in1k_20220721_150508.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f12c0457.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_172050.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -91,8 +91,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>69.2</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220725_112248.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220730_165101.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simclr/simclr_resnet50_16xb256-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220825-85fcc4de.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/simclr_resnet50_16xb256-coslr-800e_in1k_20220725_112248.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-b80ae1e5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simclr/simclr_resnet50_16xb256-coslr-800e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220730_165101.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -102,8 +102,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>256</td>
|
||||
<td>67.5</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220721_215805.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220724_172046.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220825-b6d23c86.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/mocov2_resnet50_8xb32-coslr-200e_in1k_20220721_215805.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-994c4128.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov2/mocov2_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220724_172046.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -113,8 +113,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>71.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220721_150515.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_130251.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/byol/byol_resnet50_16xb256-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220825-de817331.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/byol_resnet50_16xb256-coslr-200e_in1k_20220721_150515.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-7596c6f5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/byol/byol_resnet50_16xb256-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220724_130251.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -124,8 +124,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>256</td>
|
||||
<td>70.5</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220728_141003.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220802_145230.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220825-5b3fc7fc.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20220728_141003.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-80341e08.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220802_145230.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -135,8 +135,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>256</td>
|
||||
<td>63.5</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220727_221415.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220730_091650.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220825-3078723b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/densecl_resnet50_8xb32-coslr-200e_in1k_20220727_221415.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-steplr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220825-f0f0a579.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/densecl/densecl_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb32-steplr-100e_in1k/resnet50_linear-8xb32-steplr-100e_in1k_20220730_091650.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -146,8 +146,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>256</td>
|
||||
<td>68.3</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220725_224724.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220804_175115.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220825-d07cb2e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/simsiam_resnet50_8xb32-coslr-100e_in1k_20220725_224724.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-f53ba400.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220804_175115.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -156,8 +156,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>256</td>
|
||||
<td>69.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220726_033722.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220802_120717.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220825-efe91299.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/simsiam_resnet50_8xb32-coslr-200e_in1k_20220726_033722.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb512-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220825-519b5135.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k/resnet50_linear-8xb512-coslr-90e_in1k/resnet50_linear-8xb512-coslr-90e_in1k_20220802_120717.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -167,8 +167,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>71.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220726_033718.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220730_093018.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220825-57307488.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/barlowtwins_resnet50_8xb256-coslr-300e_in1k_20220726_033718.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb32-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220825-52fde35f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/barlowtwins/barlowtwins_resnet50_8xb256-coslr-300e_in1k/resnet50_linear-8xb32-coslr-100e_in1k/resnet50_linear-8xb32-coslr-100e_in1k_20220730_093018.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -178,8 +178,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>69.6</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220915_154635.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113350.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220927-f1144efa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/mocov3_resnet50_8xb512-amp-coslr-100e_in1k_20220915_154635.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-8f7d937e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-100e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113350.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -188,8 +188,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>72.8</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220915_180538.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113403.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220927-1e4f3304.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/mocov3_resnet50_8xb512-amp-coslr-300e_in1k_20220915_180538.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-d21ddac2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-300e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220920_113403.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -198,8 +198,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>74.4</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220919_111209.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220926_102021.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220927-e043f51a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/mocov3_resnet50_8xb512-amp-coslr-800e_in1k_20220919_111209.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/resnet50_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220927-0e97a483.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_resnet50_8xb512-amp-coslr-800e_in1k/resnet50_linear-8xb128-coslr-90e_in1k/resnet50_linear-8xb128-coslr-90e_in1k_20220926_102021.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -208,8 +208,8 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>73.6</td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220721_153833.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-small-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220724_140850.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220826-08bc52f7.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k-224_20220721_153833.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-small-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220826-376674ef.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-small-p16_16xb256-amp-coslr-300e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k/vit-small-p16_linear-8xb128-coslr-90e_in1k_20220724_140850.json'>log</a></td>
|
||||
<td>/</td>
|
||||
</tr>
|
||||
<tr>
|
||||
|
|
@ -218,9 +218,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>76.9</td>
|
||||
<td>83.0</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220725_104223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220729_004628.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb64-coslr-150e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220809_103500.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220826-25213343.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k-224_20220725_104223.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb128-coslr-90e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220826-83be7758.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k/vit-base-p16_linear-8xb128-coslr-90e_in1k_20220729_004628.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb64-coslr-150e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220826-f1e6c442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-base-p16_16xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k/vit-base-p16_ft-8xb64-coslr-150e_in1k_20220809_103500.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -228,9 +228,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>/</td>
|
||||
<td>83.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220818_143032.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220829-9b88a442.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k-224_20220818_143032.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb64-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220825_201433.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb64-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220829-878a2f7f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mocov3/mocov3_vit-large-p16_64xb64-amp-coslr-300e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k/vit-large-p16_ft-8xb64-coslr-100e_in1k_20220825_201433.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="9">MAE</td>
|
||||
|
|
@ -239,9 +239,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>60.8</td>
|
||||
<td>82.8</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220718_152424.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220720_104514.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220713_140138.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220829-c2cf66ba.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/mae_vit-base-p16_8xb512-coslr-300e-fp16_in1k_20220718_152424.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220720_104514.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220713_140138.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -249,9 +249,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>62.5</td>
|
||||
<td>83.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220628_200815.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220713_142534.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220708_183134.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220825-bc79e40b.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-base-p16_8xb512-coslr-400e-fp16_in1k_20220628_200815.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220713_142534.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220708_183134.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -259,9 +259,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>65.1</td>
|
||||
<td>83.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220718_134405.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k20220721_203941.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220724_232940.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220825-5d81fbc4.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-base-p16_8xb512-coslr-800e-fp16_in1k_20220718_134405.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k20220721_203941.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220724_232940.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -269,9 +269,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>67.1</td>
|
||||
<td>83.5</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220815_103458.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220724_232557.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220721_202304.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-base-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220825-f7569ca2.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k_20220815_103458.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k/vit-base-p16_linear-8xb2048-coslr-90e_in1k_20220724_232557.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220825-cf70aa21.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-base-p16_8xb512-fp16-coslr-1600e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20220721_202304.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -279,9 +279,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>70.7</td>
|
||||
<td>85.2</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220726_202204.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220803_101331.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220729_122511.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220825-b11d0425.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k_20220726_202204.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220803_101331.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-400e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220729_122511.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -289,9 +289,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>73.7</td>
|
||||
<td>85.4</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220804_104018.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220808_092730.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220730_235819.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-800e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220825-df72726a.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k_20220804_104018.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220808_092730.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-800e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220730_235819.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-large</td>
|
||||
|
|
@ -299,9 +299,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>75.5</td>
|
||||
<td>85.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220806_210725.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220813_155615.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220813_125305.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-large-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220825-cc7e98c9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k_20220806_210725.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_linear-8xb2048-coslr-90e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k/vit-large-p16_linear-8xb2048-coslr-90e_in1k_20220813_155615.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-large-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | model | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-large-p16_8xb512-fp16-coslr-1600e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k/vit-large-p16_ft-8xb128-coslr-50e_in1k_20220813_125305.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-huge-FT-224</td>
|
||||
|
|
@ -309,9 +309,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>/</td>
|
||||
<td>86.9</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220829_114027.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-8xb128-coslr-50e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220916-0bfc9bfd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k/vit-huge-p16_ft-8xb128-coslr-50e_in1k_20220829_114027.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-huge-FT-448</td>
|
||||
|
|
@ -319,9 +319,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>/</td>
|
||||
<td>87.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/mae_vit-huge-p16_8xb512-amp-coslr-1600e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220916-ff848775.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k_20220814_135241.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220913_113737.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220916-95b6a0ce.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mae/mae_vit-huge-p16_8xb512-fp16-coslr-1600e_in1k/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448/vit-huge-p16_ft-32xb8-coslr-50e_in1k-448_20220913_113737.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>CAE</td>
|
||||
|
|
@ -330,9 +330,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/cae/cae_vit-base-p16_16xb128-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220825-404a1929.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220615_163141.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/cae/cae_vit-base-p16_16xb128-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220825-404a1929.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k_20220615_163141.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220711_165500.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220825-f3d234cd.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/cae/cae_vit-base-p16_16xb128-fp16-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k/vit-base-p16_ft-8xb128-coslr-100e-rpe_in1k_20220711_165500.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="4">SimMIM</td>
|
||||
|
|
@ -341,9 +341,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>82.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829_001452.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829-9cf23aa1.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k/swin-base_ft-8xb256-coslr-100e_in1k_20220829_001452.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Swin-base-FT224</td>
|
||||
|
|
@ -351,9 +351,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.5</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-100e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220829-0e15782d.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192/simmim_swin-base_8xb256-amp-coslr-100e_in1k-192_20220827_034052.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | model | log</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | model | log</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Swin-base-FT224</td>
|
||||
|
|
@ -361,9 +361,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220906_141645.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220916-a0e931ac.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192_20220906_141645.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221207_135847.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-base_ft-8xb256-coslr-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221208-155cc6e6.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-base_16xb128-amp-coslr-800e_in1k-192/swin-base_ft-8xb256-coslr-100e_in1k-224/swin-base_ft-8xb256-coslr-100e_in1k-224_20221207_135847.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Swin-large-FT224</td>
|
||||
|
|
@ -371,9 +371,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>84.8</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220907_203738.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220916-4ad216d3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192_20220907_203738.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220914_133331.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220916-d4865790.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/simmim/simmim_swin-large_16xb128-amp-coslr-800e_in1k-192/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224/swin-large_ft-8xb256-coslr-ws14-100e_in1k-224_20220914_133331.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MaskFeat</td>
|
||||
|
|
@ -382,9 +382,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.4</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221019_194256.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221101-6dfc8bf3.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221019_194256.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221026_105344.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/benchmarks/classification/imagenet/vit-base-p16_ft-8xb256-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221028-5134431c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k/vit-base-p16_ft-8xb256-coslr-100e_in1k_20221026_105344.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>BEiT</td>
|
||||
|
|
@ -393,9 +393,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>83.1</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221128-ab79e626.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221123_103802.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221128-ab79e626.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221123_103802.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beit/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221128-0ca393e9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221127_162126.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beit/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221128-0ca393e9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beit/beit_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221127_162126.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MILAN</td>
|
||||
|
|
@ -404,9 +404,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>78.9</td>
|
||||
<td>85.3</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221123_112721.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221125_031826.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221124_215401.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221129-180922e8.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k_20221123_112721.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221129-74ac94fa.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k-milan_20221125_031826.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/milan/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221129-03f26f85.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/milan/milan_vit-base-p16_16xb256-amp-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221124_215401.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>BEiT v2</td>
|
||||
|
|
@ -415,9 +415,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>85.0</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221206_012130.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221212-a157be30.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k_20221206_012130.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/beitv2/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221211_155017.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/beitv2/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221212-d1c0789e.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/beitv2/beitv2_vit-base-p16_8xb256-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221211_155017.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>EVA</td>
|
||||
|
|
@ -426,9 +426,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>69.0</td>
|
||||
<td>83.7</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221220_113809.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/elfsup/eva/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221222_134137.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/eva/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221221_212618.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221226-26d90f07.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k_20221220_113809.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/elfsup/eva/classification/vit-base-p16_linear-8xb2048-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221226-ef51bf09.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k/vit-base-p16_linear-8xb2048-coslr-100e_in1k_20221222_134137.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/eva/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221226-f61cf992.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/eva/eva-mae-style_vit-base-p16_16xb256-coslr-400e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20221221_212618.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MixMIM</td>
|
||||
|
|
@ -437,9 +437,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>2048</td>
|
||||
<td>/</td>
|
||||
<td>84.6</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221204_134711.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221208-44fe8d2c.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_16xb128-coslr-300e_in1k_20221204_134711.json'>log</a></td>
|
||||
<td>/</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/configs/selfsup/mixmim/classification/mixmim-base-p16_ft-8xb128-coslr-100e-in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221206_143046.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mixmim/classification/mixmim-base-p16_ft-8xb128-coslr-100e-in1k.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221208-41ecada9.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/mixmim/mixmim-base-p16_16xb128-coslr-300e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k/mixmim-base-p16_ft-8xb128-coslr-100e_in1k_20221206_143046.json'>log</a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td rowspan="2">PixMIM</td>
|
||||
|
|
@ -448,9 +448,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>63.3</td>
|
||||
<td>83.1</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k_20230322-3304a88c.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-72322af8.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-300e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-7eba2bc2.json'> log </a></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>ViT-base</td>
|
||||
|
|
@ -458,9 +458,9 @@ ImageNet 有多个版本，不过最常用的是 ILSVRC 2012。我们提供了
|
|||
<td>4096</td>
|
||||
<td>67.5</td>
|
||||
<td>83.5</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k_20230322-e8137924.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_linear-8xb2048-coslr-torchvision-transform-90e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k/vit-base-p16_linear-8xb2048-torchvision-transform-coslr-90e_in1k_20230322-12c15568.json'> log </a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/pixmim/classification/vit-base-p16_ft-8xb128-coslr-100e_in1k.py'> config </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.pth'> model </a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/pixmim/pixmim_vit-base-p16_8xb512-amp-coslr-800e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k/vit-base-p16_ft-8xb128-coslr-100e_in1k_20230322-616b1a7f.json'> log </a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ MMCV, MMClassification, MMDetection and MMSegmentation 的版本兼容性如下
|
|||
|
||||
## DeepCluster 在 A100 GPU
|
||||
|
||||
如果您想尝试 [DeepCluster](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/deepcluster/README.md) 在 A100 GPU 上，使用 pip 安装 `faiss` 将会引发错误，
|
||||
如果您想尝试 [DeepCluster](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/deepcluster/README.md) 在 A100 GPU 上，使用 pip 安装 `faiss` 将会引发错误，
|
||||
他在[这里](https://github.com/facebookresearch/faiss/issues/2076)被提及过。
|
||||
|
||||
请使用 conda 安装：
|
||||
|
|
|
|||
|
|
@ -7,7 +7,7 @@ from modelindex.load_model_index import load
|
|||
|
||||
MMSELFSUP_ROOT = Path(__file__).absolute().parents[2]
|
||||
PAPERS_ROOT = Path('papers') # Path to save generated paper pages.
|
||||
GITHUB_PREFIX = 'https://github.com/open-mmlab/mmselfsup/blob/1.x/'
|
||||
GITHUB_PREFIX = 'https://github.com/open-mmlab/mmselfsup/blob/main/'
|
||||
MODELZOO_TEMPLATE = """
|
||||
# 模型库数据汇总
|
||||
|
||||
|
|
|
|||
|
|
@ -1,3 +1,3 @@
|
|||
## <a href='https://mmselfsup.readthedocs.io/en/dev-1.x/'>English</a>
|
||||
## <a href='https://mmselfsup.readthedocs.io/en/latest/'>English</a>
|
||||
|
||||
## <a href='https://mmselfsup.readthedocs.io/zh_CN/dev-1.x/'>简体中文</a>
|
||||
## <a href='https://mmselfsup.readthedocs.io/zh_CN/latest/'>简体中文</a>
|
||||
|
|
|
|||
|
|
@ -81,8 +81,8 @@ bash tools/dataset_converters/prepare_voc07_cls.sh $YOUR_DATA_ROOT
|
|||
|
||||
### 检测
|
||||
|
||||
您可以参考 [mmdetection](https://github.com/open-mmlab/mmdetection/blob/dev-3.x/docs/en/1_exist_data_model.md) 来准备 COCO，VOC2007 和 VOC2012 检测数据集。
|
||||
您可以参考 [mmdetection](https://github.com/open-mmlab/mmdetection/blob/main/docs/en/1_exist_data_model.md) 来准备 COCO，VOC2007 和 VOC2012 检测数据集。
|
||||
|
||||
### 分割
|
||||
|
||||
您可以参考 [mmsegmentation](https://github.com/open-mmlab/mmsegmentation/blob/dev-1.x/docs/en/user_guides/2_dataset_prepare.md#prepare-datasets) 来准备 VOC2012AUG 和 Cityscapes 分割数据集。
|
||||
您可以参考 [mmsegmentation](https://github.com/open-mmlab/mmsegmentation/blob/main/docs/en/user_guides/2_dataset_prepare.md#prepare-datasets) 来准备 VOC2012AUG 和 Cityscapes 分割数据集。
|
||||
|
|
|
|||
|
|
@ -84,7 +84,7 @@ NNODES=2 NODE_RANK=1 PORT=${MASTER_PORT} MASTER_ADDR=${MASTER_ADDR} sh tools/dis
|
|||
|
||||
但是，如果您不使用高速网路连接这几台机器的话，训练将会非常慢。
|
||||
|
||||
如果您使用的是 **slurm** 来管理多台机器，您可以使用同在单台机器上一样的命令来启动任务，但是您必须得设置合适的环境变量和参数，具体可以参考 [slurm_train.sh](https://github.com/open-mmlab/mmselfsup/blob/master/tools/slurm_train.sh)。
|
||||
如果您使用的是 **slurm** 来管理多台机器，您可以使用同在单台机器上一样的命令来启动任务，但是您必须得设置合适的环境变量和参数，具体可以参考 [slurm_train.sh](https://github.com/open-mmlab/mmselfsup/blob/main/tools/slurm_train.sh)。
|
||||
|
||||
### 在一台机器上启动多个任务
|
||||
|
||||
|
|
|
|||
|
|
@ -190,7 +190,7 @@ resume = True
|
|||
## 在COCO数据集上使用MAE算法进行预训练
|
||||
|
||||
```{note}
|
||||
你可能需要参考[文档](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/get_started.md)安装MMDetection 来使用 `mmdet.CocoDataset`。
|
||||
你可能需要参考[文档](https://github.com/open-mmlab/mmdetection/blob/main/docs/en/get_started.md)安装MMDetection 来使用 `mmdet.CocoDataset`。
|
||||
```
|
||||
|
||||
与在自定义数据集上进行预训练类似，我们在本教程中也提供了一个使用COCO数据集进行预训练的示例。修改后的文件如下：
|
||||
|
|
|
|||
|
|
@ -130,7 +130,7 @@ bash tools/benchmarks/classification/knn_imagenet/slurm_test_knn.sh ${PARTITION}
|
|||
- `${SELFSUP_CONFIG}`：是自监督实验的配置文件。
|
||||
- `${CHECKPOINT}`：检查点模型文件的路径。
|
||||
- 如果您想改变GPU的数量，您可以在命令的前面加上`GPUS_PER_NODE=4 GPUS=4`。
|
||||
- `[optional arguments]`：用于可选参数，您可以参考这个[脚本](https://github.com/open-mmlab/mmselfsup/blob/1.x/tools/benchmarks/classification/knn_imagenet/test_knn.py)
|
||||
- `[optional arguments]`：用于可选参数，您可以参考这个[脚本](https://github.com/open-mmlab/mmselfsup/blob/main/tools/benchmarks/classification/knn_imagenet/test_knn.py)
|
||||
|
||||
命令的一个例子
|
||||
|
||||
|
|
|
|||
|
|
@ -49,7 +49,7 @@ def after_train_iter(...):
|
|||
|
||||
(2) 浏览数据集
|
||||
|
||||
[`add_datasample()`](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/mmselfsup/visualization/selfsup_visualizer.py#L151) 函数位于 [`SelfSupVisualizer`](mmselfsup.visualization.SelfSupVisualizer), 常用于在 [browse_dataset.py](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/analysis_tools/browse_dataset.py) 中浏览数据集。更多细节可以参考 [数据集可视化](#数据集可视化)。
|
||||
[`add_datasample()`](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/visualization/selfsup_visualizer.py#L151) 函数位于 [`SelfSupVisualizer`](mmselfsup.visualization.SelfSupVisualizer), 常用于在 [browse_dataset.py](https://github.com/open-mmlab/mmselfsup/blob/main/tools/analysis_tools/browse_dataset.py) 中浏览数据集。更多细节可以参考 [数据集可视化](#数据集可视化)。
|
||||
|
||||
## 用不同的存储后端
|
||||
|
||||
|
|
@ -129,7 +129,7 @@ python tools/analysis_tools/visualize_tsne.py ${CONFIG_FILE} --checkpoint ${CKPT
|
|||
- `CONFIG_FILE`: 位于 `configs/tsne/` 中的 t-SNE 的配置文件。
|
||||
- `CKPT_PATH`: 模型检查点的目录或链接。
|
||||
- `WORK_DIR`: 拿来存可视化结果的目录。
|
||||
- `[optional arguments]`: 可选项，可以参考 [visualize_tsne.py](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/analysis_tools/visualize_tsne.py)
|
||||
- `[optional arguments]`: 可选项，可以参考 [visualize_tsne.py](https://github.com/open-mmlab/mmselfsup/blob/main/tools/analysis_tools/visualize_tsne.py)
|
||||
|
||||
一个命令示例如下：
|
||||
|
||||
|
|
@ -171,7 +171,7 @@ python tools/analysis_tools/visualize_reconstruction.py ${CONFIG_FILE} \
|
|||
- `CKPT_PATH`: 模型检查点的路径。
|
||||
- `IMAGE_PATH`: 输入图像的路径。
|
||||
- `OUTPUT_PATH`: 输出图像的路径，包含４个子图。
|
||||
- `[optional arguments]`: for optional arguments, 您可以参考 [visualize_reconstruction.py](https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/tools/analysis_tools/visualize_reconstruction.py) 了解可选参数。
|
||||
- `[optional arguments]`: for optional arguments, 您可以参考 [visualize_reconstruction.py](https://github.com/open-mmlab/mmselfsup/blob/main/tools/analysis_tools/visualize_reconstruction.py) 了解可选参数。
|
||||
|
||||
例子如下:
|
||||
|
||||
|
|
|
|||
|
|
@ -127,7 +127,7 @@ Note:
|
|||
|
||||
## Results
|
||||
|
||||
<!-- List the results as usually done in other model's README. [Example](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mae/README.md#models-and-benchmarks)
|
||||
<!-- List the results as usually done in other model's README. [Example](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/README.md#models-and-benchmarks)
|
||||
You should claim whether this is based on the pre-trained weights, which are converted from the official release; or it's a reproduced result obtained from retraining the model in this project. -->
|
||||
|
||||
If you have any downstream task results, you could list them here.
|
||||
|
|
@ -211,11 +211,11 @@ A project does not necessarily have to be finished in a single PR, but it's esse
|
|||
|
||||
- [ ] Type hints and docstrings
|
||||
|
||||
<!-- Ideally *all* the methods should have [type hints](https://www.pythontutorial.net/python-basics/python-type-hints/) and [docstrings](https://google.github.io/styleguide/pyguide.html#381-docstrings). [Example](https://github.com/open-mmlab/mmselfsup/blob/1.x/mmselfsup/models/backbones/mae_vit.py) -->
|
||||
<!-- Ideally *all* the methods should have [type hints](https://www.pythontutorial.net/python-basics/python-type-hints/) and [docstrings](https://google.github.io/styleguide/pyguide.html#381-docstrings). [Example](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/models/backbones/mae_vit.py) -->
|
||||
|
||||
- [ ] Unit tests
|
||||
|
||||
<!-- Unit tests for each module are required. [Example](https://github.com/open-mmlab/mmselfsup/blob/1.x/tests/test_models/test_backbones/test_mae_vit.py) -->
|
||||
<!-- Unit tests for each module are required. [Example](https://github.com/open-mmlab/mmselfsup/blob/main/tests/test_models/test_backbones/test_mae_vit.py) -->
|
||||
|
||||
- [ ] Code polishing
|
||||
|
||||
|
|
@ -223,6 +223,6 @@ A project does not necessarily have to be finished in a single PR, but it's esse
|
|||
|
||||
- [ ] Metafile.yml and README.md
|
||||
|
||||
<!-- It will be parsed by MIM and Inferencer. [Example](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mae/metafile.yml). In particular, you may have to refactor this README into a standard one. [Example](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mae/README.md) -->
|
||||
<!-- It will be parsed by MIM and Inferencer. [Example](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/metafile.yml). In particular, you may have to refactor this README into a standard one. [Example](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/README.md) -->
|
||||
|
||||
- [ ] Refactor and Move your modules into the core package following the codebase's file hierarchy structure.
|
||||
|
|
|
|||
|
|
@ -196,8 +196,8 @@ Due to the version of K400 dataset, our pretraining, fine-tuning and the final t
|
|||
<td>300</td>
|
||||
<td>512</td>
|
||||
<td>81.8</td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/projects/maskfeat_video/configs/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400_20230131-87d60b6f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400_20230118_114151.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/dev-1.x/projects/maskfeat_video/configs/mvit-small_ft-8xb16-coslr-100e_k400.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400/mvit-small_ft-8xb16-coslr-100e_k400/mvit-small_ft-8xb16-coslr-100e_k400_20230131-5e8303f5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400/mvit-small_ft-8xb16-coslr-100e_k400/mvit-small_ft-8xb16-coslr-100e_k400_20230121_142927.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/projects/maskfeat_video/configs/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400_20230131-87d60b6f.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400_20230118_114151.json'>log</a></td>
|
||||
<td><a href='https://github.com/open-mmlab/mmselfsup/blob/main/projects/maskfeat_video/configs/mvit-small_ft-8xb16-coslr-100e_k400.py'>config</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400/mvit-small_ft-8xb16-coslr-100e_k400/mvit-small_ft-8xb16-coslr-100e_k400_20230131-5e8303f5.pth'>model</a> | <a href='https://download.openmmlab.com/mmselfsup/1.x/maskfeat/maskfeat_mvit-small_16xb32-amp-coslr-300e_k400/mvit-small_ft-8xb16-coslr-100e_k400/mvit-small_ft-8xb16-coslr-100e_k400_20230121_142927.json'>log</a></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
|
@ -258,11 +258,11 @@ A project does not necessarily have to be finished in a single PR, but it's esse
|
|||
|
||||
- [ ] Type hints and docstrings
|
||||
|
||||
<!-- Ideally *all* the methods should have [type hints](https://www.pythontutorial.net/python-basics/python-type-hints/) and [docstrings](https://google.github.io/styleguide/pyguide.html#381-docstrings). [Example](https://github.com/open-mmlab/mmselfsup/blob/1.x/mmselfsup/models/backbones/mae_vit.py) -->
|
||||
<!-- Ideally *all* the methods should have [type hints](https://www.pythontutorial.net/python-basics/python-type-hints/) and [docstrings](https://google.github.io/styleguide/pyguide.html#381-docstrings). [Example](https://github.com/open-mmlab/mmselfsup/blob/main/mmselfsup/models/backbones/mae_vit.py) -->
|
||||
|
||||
- [ ] Unit tests
|
||||
|
||||
<!-- Unit tests for each module are required. [Example](https://github.com/open-mmlab/mmselfsup/blob/1.x/tests/test_models/test_backbones/test_mae_vit.py) -->
|
||||
<!-- Unit tests for each module are required. [Example](https://github.com/open-mmlab/mmselfsup/blob/main/tests/test_models/test_backbones/test_mae_vit.py) -->
|
||||
|
||||
- [ ] Code polishing
|
||||
|
||||
|
|
@ -270,6 +270,6 @@ A project does not necessarily have to be finished in a single PR, but it's esse
|
|||
|
||||
- [ ] `metafile.yml` and `README.md`
|
||||
|
||||
<!-- It will be parsed by MIM and Inferencer. [Example](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mae/metafile.yml). In particular, you may have to refactor this README into a standard one. [Example](https://github.com/open-mmlab/mmselfsup/blob/1.x/configs/selfsup/mae/README.md) -->
|
||||
<!-- It will be parsed by MIM and Inferencer. [Example](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/metafile.yml). In particular, you may have to refactor this README into a standard one. [Example](https://github.com/open-mmlab/mmselfsup/blob/main/configs/selfsup/mae/README.md) -->
|
||||
|
||||
- [ ] Refactor and Move your modules into the core package following the codebase's file hierarchy structure.
|
||||
|
|
|
|||
Loading…
Reference in New Issue