From 45951c1b121fd4e4a116a22d7680efeeecb59168 Mon Sep 17 00:00:00 2001 From: Yixiao Fang <36138628+fangyixiao18@users.noreply.github.com> Date: Mon, 10 Jan 2022 16:40:47 +0800 Subject: [PATCH] [Docs] update README and model_zoo.md (#165) * [Docs] update README * [Docs] add simsiam logs * [Docs] add chinese version of model_zoo.md * [Docs] fix typo * [Benchmark] update SimSiam 100 epoch benchmark results * [Benchmark] update simsiam 100 epoch seg results --- README.md | 2 + README_zh-CN.md | 12 +++++- configs/selfsup/simsiam/README.md | 10 ++--- docs/en/model_zoo.md | 19 +++++---- docs/zh_cn/model_zoo.md | 71 ++++++++++++++++--------------- 5 files changed, 66 insertions(+), 48 deletions(-) diff --git a/README.md b/README.md index 8a3d88c1..564d8b9d 100644 --- a/README.md +++ b/README.md @@ -150,3 +150,5 @@ Remarks: - [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab few shot learning toolbox and benchmark. - [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 3D human parametric model toolbox and benchmark. - [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab self-supervised learning toolbox and benchmark. +- [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab model compression toolbox and benchmark. +- [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab model deployment framework. diff --git a/README_zh-CN.md b/README_zh-CN.md index 0cff19ea..dad5cd4f 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -40,6 +40,14 @@ MMSelfSup 是一个基于 PyTorch 实现的开源自监督表征学习工具箱 该项目采用 [Apache 2.0 开源许可证](LICENSE). +## 修改日志 + +MMSelfSup **v0.5.0** 在 16/12/2021 发版. + +请参考 [changelog.md](docs/zh_cn/changelog.md) 获取更多细节和历史版本信息。 + +MMSelfSup 和 OpenSelfSup 的不同点写在 [compatibility.md](docs/en/compatibility.md) 当中。 + ## 模型库和基准测试 ### 模型库 @@ -136,13 +144,15 @@ MMSelfSup 是一款由不同学校和公司共同贡献的开源项目，我们 - [MMFewShot](https://github.com/open-mmlab/mmfewshot): OpenMMLab 少样本学习工具箱与测试基准 - [MMHuman3D](https://github.com/open-mmlab/mmhuman3d): OpenMMLab 人体参数化模型工具箱与测试基准 - [MMSelfSup](https://github.com/open-mmlab/mmselfsup): OpenMMLab 自监督学习工具箱与测试基准 +- [MMRazor](https://github.com/open-mmlab/mmrazor): OpenMMLab 模型压缩工具箱与测试基准 +- [MMDeploy](https://github.com/open-mmlab/mmdeploy): OpenMMLab 模型部署框架 ## 欢迎加入 OpenMMLab 社区 扫描下方的二维码可关注 OpenMMLab 团队的 [知乎官方账号](https://www.zhihu.com/people/openmmlab)，加入 OpenMMLab 团队的 [官方交流 QQ 群](https://jq.qq.com/?_wv=1027&k=GJP18SjI)，添加OpenMMLab 官方小助手微信，加入 MMSelfSup 微信社区。
- +
我们会在 OpenMMLab 社区为大家 diff --git a/configs/selfsup/simsiam/README.md b/configs/selfsup/simsiam/README.md index ea01158b..b9a4a7f1 100644 --- a/configs/selfsup/simsiam/README.md +++ b/configs/selfsup/simsiam/README.md @@ -42,7 +42,7 @@ 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](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | feature5 | 84.21 | 39.71 | 49.65 | 62.79 | 69.97 | 74.73 | 78.30 | 81.06 | 82.44 | +| [resnet50_8xb32-coslr-100e](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](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 @@ -53,7 +53,7 @@ The **AvgPool** result is obtained from Linear Evaluation with GlobalAveragePool | Self-Supervised Config | Feature1 | Feature2 | Feature3 | Feature4 | Feature5 | AvgPool | | ---------------------------------------------------------------------- | -------- | -------- | -------- | -------- | -------- | ------- | -| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 15.85 | 34.02 | 46.00 | 60.90 | 67.92 | 67.88 | +| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 16.27 | 33.77 | 45.80 | 60.83 | 68.21 | 68.20 | | [resnet50_8xb32-coslr-200e](simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 15.57 | 37.21 | 47.28 | 62.21 | 69.85 | 69.80 | @@ -67,7 +67,7 @@ Please refer to [faster_rcnn_r50_c4_mstrain_24k_voc0712.py](../../benchmarks/mmd | Self-Supervised Config | AP50 | | ---------------------------------------------------------------------- | ----- | -| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 79.97 | +| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 79.80 | | [resnet50_8xb32-coslr-200e](simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 79.85 | #### COCO2017 @@ -76,7 +76,7 @@ Please refer to [mask_rcnn_r50_fpn_mstrain_1x_coco.py](../../benchmarks/mmdetect | Self-Supervised Config | mAP(Box) | AP50(Box) | AP75(Box) | mAP(Mask) | AP50(Mask) | AP75(Mask) | | ---------------------------------------------------------------------- | -------- | --------- | --------- | --------- | ---------- | ---------- | -| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.3 | 57.6 | 41.7 | 34.4 | 54.8 | 36.9 | +| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.6 | 57.6 | 42.3 | 34.6 | 54.8 | 36.9 | | [resnet50_8xb32-coslr-200e](simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 38.8 | 58.0 | 42.3 | 34.9 | 55.3 | 37.6 | ### Segmentation @@ -89,5 +89,5 @@ Please refer to [fcn_r50-d8_512x512_20k_voc12aug.py](../../benchmarks/mmsegmenta | Self-Supervised Config | mIOU | | ---------------------------------------------------------------------- | ----- | -| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 46.11 | +| [resnet50_8xb32-coslr-100e](simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 48.35 | | [resnet50_8xb32-coslr-200e](simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 46.27 | diff --git a/docs/en/model_zoo.md b/docs/en/model_zoo.md index 50a24e8e..718014bf 100644 --- a/docs/en/model_zoo.md +++ b/docs/en/model_zoo.md @@ -1,6 +1,6 @@ # Model Zoo -All models and benchmarks results are recorded below. +All models and part of benchmark results are recorded below. ## Pre-trained models @@ -16,16 +16,19 @@ All models and benchmarks results are recorded below. | [Relative Location](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/README.md) | [relative-loc_resnet50_8xb64-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k_20211213-cdd3162f.pth) | [log](https://download.openmmlab.com/mmselfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k_20210930_144754.log.json) | | [Rotation Prediction](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/README.md) | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20211213-513972ac.pth) | [log](https://download.openmmlab.com/mmselfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20210930_151459.log.json) | | [SimCLR](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/README.md) | [simclr_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k_20211213-d0e53669.pth) | -| [SimSiam](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/README.md) | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k_20211213-925d628c.pth) | -| | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k_20211213-b605f9f1.pth) | +| [SimSiam](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/README.md) | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k_20211230-65a0eff4.pth) | [log](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k_20211225_132004.log.json) | +| | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k_20211213-b605f9f1.pth) | [log](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k_20211225_132031.log.json) | | [SwAV](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/swav/README.md) | [swav_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) | [model](https://download.openmmlab.com/mmselfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20211213-0028900c.pth) | [log](https://download.openmmlab.com/mmselfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20211206_102636.log.json) | Remarks: -- If not specified, the models are trained 200 epochs. +- The training details are recorded in the config names. + +- You can click algorithm name to obtain more information. + ## Benchmarks -In following tables, we only displayed ImageNet Linear Evaluation, COCO17 Object Detection and PASCAL VOC12 Aug Segmentation, you can click the model name above to get the comprehensive benchmark results. +In following tables, we only displayed ImageNet Linear Evaluation, COCO17 Object Detection and PASCAL VOC12 Aug Segmentation, you can click algorithm name above to check the comprehensive benchmark results. ### ImageNet Linear Evaluation @@ -42,7 +45,7 @@ If not specified, we use linear evaluation setting from [MoCo](http://openaccess | Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | | 39.65 | | Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | | 44.35 | | SimCLR | [simclr_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | | 58.92 | -| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | SimSiam paper setting | 67.88 | +| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | SimSiam paper setting | 68.20 | | | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | SimSiam paper setting | 69.80 | | SwAV | [swav_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) | SwAV paper setting | 70.55 | @@ -59,7 +62,7 @@ In COCO17 Object detection task, we choose the evluation protocol from [MoCo](ht | Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 37.5 | 33.7 | | Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 37.9 | 34.2 | | SimCLR | [simclr_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 38.7 | 34.9 | -| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.3 | 34.4 | +| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.6 | 34.6 | | | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 38.8 | 34.9 | | SwAV | [swav_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 | 36.3 | @@ -78,6 +81,6 @@ In Pascal VOC12 Aug Segmentation task, we choose the evluation protocol from [MM | Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 63.49 | | Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 64.31 | | SimCLR | [simclr_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 64.03 | -| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 46.11 | +| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 48.35 | | | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 46.27 | | SwAV | [swav_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 | diff --git a/docs/zh_cn/model_zoo.md b/docs/zh_cn/model_zoo.md index 50a24e8e..b3424f12 100644 --- a/docs/zh_cn/model_zoo.md +++ b/docs/zh_cn/model_zoo.md @@ -1,10 +1,10 @@ -# Model Zoo +# 模型库 -All models and benchmarks results are recorded below. +所有模型和部分基准测试如下。 -## Pre-trained models +## 预训练模型 -| Algorithm | Config | Download | +| 算法 | 配置文件 | 下载链接 | | ------------------------------------------------------------------------------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | [BYOL](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/byol/README.md) | [byol_resnet50_8xb32-accum16-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k_20211213-30dbaef1.pth) | [log](https://download.openmmlab.com/mmselfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k_20211111_212813.log.json) | | | [byol_resnet50_8xb32-accum16-coslr-300e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-300e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/byol/byol_resnet50_8xb32-accum16-coslr-300e_in1k_20211213-47673e22.pth) | [log](https://download.openmmlab.com/mmselfsup/byol/byol_resnet50_8xb32-accum16-coslr-300e_in1k_20211129_163841.log.json) | @@ -16,41 +16,44 @@ All models and benchmarks results are recorded below. | [Relative Location](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/README.md) | [relative-loc_resnet50_8xb64-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k_20211213-cdd3162f.pth) | [log](https://download.openmmlab.com/mmselfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k_20210930_144754.log.json) | | [Rotation Prediction](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/README.md) | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20211213-513972ac.pth) | [log](https://download.openmmlab.com/mmselfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k_20210930_151459.log.json) | | [SimCLR](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/README.md) | [simclr_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k_20211213-d0e53669.pth) | -| [SimSiam](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/README.md) | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k_20211213-925d628c.pth) | -| | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k_20211213-b605f9f1.pth) | +| [SimSiam](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/README.md) | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k_20211230-65a0eff4.pth) | [log](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k_20211225_132004.log.json) | +| | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | [model](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k_20211213-b605f9f1.pth) | [log](https://download.openmmlab.com/mmselfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k_20211225_132031.log.json) | | [SwAV](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/swav/README.md) | [swav_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) | [model](https://download.openmmlab.com/mmselfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20211213-0028900c.pth) | [log](https://download.openmmlab.com/mmselfsup/swav/swav_resnet50_8xb32-mcrop-2-6-coslr-200e_in1k-224-96_20211206_102636.log.json) | -Remarks: +备注： -- If not specified, the models are trained 200 epochs. -## Benchmarks +- 训练细节记录在配置文件名中。 -In following tables, we only displayed ImageNet Linear Evaluation, COCO17 Object Detection and PASCAL VOC12 Aug Segmentation, you can click the model name above to get the comprehensive benchmark results. +- 可以点击算法名获得更加全面的信息。 -### ImageNet Linear Evaluation +## 基准测试 -If not specified, we use linear evaluation setting from [MoCo](http://openaccess.thecvf.com/content_CVPR_2020/papers/He_Momentum_Contrast_for_Unsupervised_Visual_Representation_Learning_CVPR_2020_paper.pdf). Or the settings is mentioned in Remark. +在下列表格中，我们只展示了基于 ImageNet 数据集的线性评估，COCO17 数据集的目标检测和 PASCAL VOC12 Aug 数据集的分割任务，您可以点击预训练模型表格中的算法名查看其它基准测试结果。 -| Algorithm | Config | Remarks | Top-1 (%) | -| ------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------- | --------- | -| BYOL | [byol_resnet50_8xb32-accum16-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | | 67.68 | -| DeepCLuster | [deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | | 46.92 | -| DenseCL | [densecl_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | | 63.34 | -| MoCo v2 | [mocov2_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/moco/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | | 67.56 | -| NPID | [npid_resnet50_8xb32-steplr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | | 58.16 | -| ODC | [odc_resnet50_8xb64-steplr-440e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | | 53.42 | -| Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | | 39.65 | -| Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | | 44.35 | -| SimCLR | [simclr_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | | 58.92 | -| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | SimSiam paper setting | 67.88 | -| | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | SimSiam paper setting | 69.80 | -| SwAV | [swav_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) | SwAV paper setting | 70.55 | +### ImageNet 线性评估 -### COCO17 Object Detection +如果没有特殊说明，下列实验采用 [MoCo](http://openaccess.thecvf.com/content_CVPR_2020/papers/He_Momentum_Contrast_for_Unsupervised_Visual_Representation_Learning_CVPR_2020_paper.pdf) 的设置，或者采用的训练设置写在备注中。 -In COCO17 Object detection task, we choose the evluation protocol from [MoCo](http://openaccess.thecvf.com/content_CVPR_2020/papers/He_Momentum_Contrast_for_Unsupervised_Visual_Representation_Learning_CVPR_2020_paper.pdf), with Mask-RCNN architecture, the results below are trained with the same [config](https://github.com/open-mmlab/mmselfsup/blob/master/configs/benchmarks/mmdetection/coco/mask_rcnn_r50_fpn_mstrain_1x_coco.py). +| 算法 | 配置文件 | 备注 | Top-1 (%) | +| ------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------- | --------- | +| BYOL | [byol_resnet50_8xb32-accum16-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | | 67.68 | +| DeepCLuster | [deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | | 46.92 | +| DenseCL | [densecl_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | | 63.34 | +| MoCo v2 | [mocov2_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/moco/mocov2_resnet50_8xb32-coslr-200e_in1k.py) | | 67.56 | +| NPID | [npid_resnet50_8xb32-steplr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/npid/npid_resnet50_8xb32-steplr-200e_in1k.py) | | 58.16 | +| ODC | [odc_resnet50_8xb64-steplr-440e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/odc/odc_resnet50_8xb64-steplr-440e_in1k.py) | | 53.42 | +| Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | | 39.65 | +| Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | | 44.35 | +| SimCLR | [simclr_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | | 58.92 | +| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | SimSiam 论文设置 | 68.20 | +| | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | SimSiam 论文设置 | 69.80 | +| SwAV | [swav_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) | SwAV 论文设置 | 70.55 | -| Algorithm | Config | mAP (Box) | mAP (Mask) | +### COCO17 目标检测 + +在 COCO17 数据集的目标检测任务中，我们选用 [MoCo](http://openaccess.thecvf.com/content_CVPR_2020/papers/He_Momentum_Contrast_for_Unsupervised_Visual_Representation_Learning_CVPR_2020_paper.pdf) 的评估设置，基于 Mask-RCNN 网络架构，下列结果通过同样的 [配置文件](https://github.com/open-mmlab/mmselfsup/blob/master/configs/benchmarks/mmdetection/coco/mask_rcnn_r50_fpn_mstrain_1x_coco.py) 训练得到。 + +| 算法 | 配置文件 | mAP (Box) | mAP (Mask) | | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | ---------- | | BYOL | [byol_resnet50_8xb32-accum16-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 40.9 | 36.8 | | DenseCL | [densecl_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/densecl/densecl_resnet50_8xb32-coslr-200e_in1k.py) | | | @@ -59,15 +62,15 @@ In COCO17 Object detection task, we choose the evluation protocol from [MoCo](ht | Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 37.5 | 33.7 | | Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 37.9 | 34.2 | | SimCLR | [simclr_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 38.7 | 34.9 | -| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.3 | 34.4 | +| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 38.6 | 34.6 | | | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 38.8 | 34.9 | | SwAV | [swav_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 | 36.3 | -### Pascal VOC12 Aug Segmentation +### Pascal VOC12 Aug 分割 -In Pascal VOC12 Aug Segmentation task, we choose the evluation protocol from [MMSeg](https://github.com/open-mmlab/mmsegmentation), with FCN architecture, the results below are trained with the same [config](configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_512x512_20k_voc12aug.py). +在 Pascal VOC12 Aug 分割任务中，我们选用 [MMSeg](https://github.com/open-mmlab/mmsegmentation) 的评估设置, 基于 FCN 网络架构, 下列结果通过同样的 [配置文件](configs/benchmarks/mmsegmentation/voc12aug/fcn_r50-d8_512x512_20k_voc12aug.py) 训练得到。 -| Algorithm | Config | mIOU | +| 算法 | 配置文件 | mIOU | | ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ----- | | BYOL | [byol_resnet50_8xb32-accum16-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/byol/byol_resnet50_8xb32-accum16-coslr-200e_in1k.py) | 67.16 | | DeepCLuster | [deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/deepcluster/deepcluster-sobel_resnet50_8xb64-steplr-200e_in1k.py) | 59.69 | @@ -78,6 +81,6 @@ In Pascal VOC12 Aug Segmentation task, we choose the evluation protocol from [MM | Relative Location | [relative-loc_resnet50_8xb64-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/relative_loc/relative-loc_resnet50_8xb64-steplr-70e_in1k.py) | 63.49 | | Rotation Prediction | [rotation-pred_resnet50_8xb16-steplr-70e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/rotation_pred/rotation-pred_resnet50_8xb16-steplr-70e_in1k.py) | 64.31 | | SimCLR | [simclr_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simclr/simclr_resnet50_8xb32-coslr-200e_in1k.py) | 64.03 | -| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 46.11 | +| SimSiam | [simsiam_resnet50_8xb32-coslr-100e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-100e_in1k.py) | 48.35 | | | [simsiam_resnet50_8xb32-coslr-200e_in1k](https://github.com/open-mmlab/mmselfsup/blob/master/configs/selfsup/simsiam/simsiam_resnet50_8xb32-coslr-200e_in1k.py) | 46.27 | | SwAV | [swav_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 |