mirror of https://github.com/alibaba/EasyCV.git
update readme.md
wenmeng.zwm
parent
7b19fefb9d
commit
80ca821518
33
README.md
33
README.md
|
|
@ -22,7 +22,6 @@ English | [简体中文](README_zh-CN.md)
|
|||
|
||||
EasyCV is an all-in-one computer vision toolbox based on PyTorch, mainly focuses on self-supervised learning, transformer based models, and major CV tasks including image classification, metric-learning, object detection, pose estimation and so on.
|
||||
|
||||
[🔥 Latest News] We have released our YOLOX-PAI that achieves SOTA results within 40~50 mAP (less than 1ms). And we also provide a convenient and fast export/predictor api for end2end object detection. To get a quick start of YOLOX-PAI, click [here](docs/source/tutorials/yolox.md)!
|
||||
|
||||
### Major features
|
||||
|
||||
|
|
@ -45,6 +44,20 @@ EasyCV is an all-in-one computer vision toolbox based on PyTorch, mainly focuses
|
|||
|
||||
EasyCV supports multi-gpu and multi worker training. EasyCV uses [DALI](https://github.com/NVIDIA/DALI) to accelerate data io and preprocessing process, and uses [TorchAccelerator](https://github.com/alibaba/EasyCV/tree/master/docs/source/tutorials/torchacc.md) and fp16 to accelerate training process. For inference optimization, EasyCV exports model using jit script, which can be optimized by [PAI-Blade](https://help.aliyun.com/document_detail/205134.html)
|
||||
|
||||
|
||||
## What's New
|
||||
|
||||
[🔥 Latest News] We have released our YOLOX-PAI that achieves SOTA results within 40~50 mAP (less than 1ms). And we also provide a convenient and fast export/predictor api for end2end object detection. To get a quick start of YOLOX-PAI, click [here](docs/source/tutorials/yolox.md)!
|
||||
|
||||
* 31/08/2022 EasyCV v0.6.0 was released.
|
||||
- Release YOLOX-PAI which achieves SOTA results within 40~50 mAP (less than 1ms)
|
||||
- Add detection algo DINO which achieves 58.5 mAP on COCO
|
||||
- Add mask2former algo
|
||||
- Releases imagenet1k, imagenet22k, coco, lvis, voc2012 data with BaiduDisk to accelerate downloading
|
||||
|
||||
Please refer to [change_log.md](docs/source/change_log.md) for more details and history.
|
||||
|
||||
|
||||
## Technical Articles
|
||||
|
||||
We have a series of technical articles on the functionalities of EasyCV.
|
||||
|
|
@ -194,24 +207,6 @@ EasyCV have collected dataset info for different senarios, making it easy for us
|
|||
|
||||
Please refer to [data_hub.md](docs/source/data_hub.md).
|
||||
|
||||
## ChangeLog
|
||||
|
||||
* 31/08/2022 EasyCV v0.6.0 was released.
|
||||
- Release YOLOX-PAI which achieves SOTA results within 40~50 mAP (less than 1ms) (#154 #172 #174 )
|
||||
- Add detection algo DINO (#144)
|
||||
- Add mask2former algo (#115)
|
||||
- Releases imagenet1k, imagenet22k, coco, lvis, voc2012 data with BaiduDisk to accelerate downloading (#145 )
|
||||
|
||||
* 28/07/2022 EasyCV v0.5.0 was released.
|
||||
|
||||
* 23/06/2022 EasyCV v0.4.0 was released.
|
||||
|
||||
* 31/04/2022 EasyCV v0.3.0 was released.
|
||||
|
||||
* 07/04/2022 EasyCV v0.2.2 was released.
|
||||
|
||||
Please refer to [change_log.md](docs/source/change_log.md) for more details and history.
|
||||
|
||||
|
||||
## License
|
||||
|
||||
|
|
|
|||
|
|
@ -22,7 +22,6 @@
|
|||
|
||||
EasyCV是一个涵盖多个领域的基于Pytorch的计算机视觉工具箱，聚焦自监督学习和视觉transformer关键技术，覆盖主流的视觉建模任务例如图像分类，度量学习，目标检测，关键点检测等。
|
||||
|
||||
[🔥 Latest News] 近期我们开源了YOLOX-PAI，在40-50mAP(推理速度小于1ms)范围内达到了业界的SOTA水平。同时EasyCV提供了一套简洁高效的模型导出和预测接口，供用户快速完成端到端的图像检测任务。如果你想快速了解YOLOX-PAI, 点击 [这里](docs/source/tutorials/yolox.md)!
|
||||
|
||||
### 核心特性
|
||||
|
||||
|
|
@ -44,6 +43,21 @@ EasyCV是一个涵盖多个领域的基于Pytorch的计算机视觉工具箱，
|
|||
|
||||
EasyCV支持多机多卡训练，同时支持[TorchAccelerator](docs/source/tutorials/torchacc.md)和fp16进行训练加速。在数据读取和预处理方面，EasyCV使用[DALI](https://github.com/NVIDIA/DALI)进行加速。对于模型推理优化，EasyCV支持使用jit script导出模型，使用[PAI-Blade](https://help.aliyun.com/document_detail/205134.html)进行模型优化。
|
||||
|
||||
|
||||
## 最新进展
|
||||
|
||||
[🔥 Latest News] 近期我们开源了YOLOX-PAI，在40-50mAP(推理速度小于1ms)范围内达到了业界的SOTA水平。同时EasyCV提供了一套简洁高效的模型导出和预测接口，供用户快速完成端到端的图像检测任务。如果你想快速了解YOLOX-PAI, 点击 [这里](docs/source/tutorials/yolox.md)!
|
||||
|
||||
* 31/08/2022 EasyCV v0.6.0 版本发布。
|
||||
- 发布YOLOX-PAI，在轻量级模型中取得SOTA效果
|
||||
- 增加检测算法DINO， COCO mAP 58.5
|
||||
- 增加Mask2Former算法
|
||||
- Datahub新增imagenet1k, imagenet22k, coco, lvis, voc2012 数据的百度网盘链接，加速下载
|
||||
|
||||
|
||||
更多版本的详细信息请参考[变更记录](docs/source/change_log.md)。
|
||||
|
||||
|
||||
## 技术文章
|
||||
|
||||
我们有一系列关于EasyCV功能的技术文章。
|
||||
|
|
@ -178,26 +192,6 @@ EasyCV是一个涵盖多个领域的基于Pytorch的计算机视觉工具箱，
|
|||
- [目标检测模型库](docs/source/model_zoo_det.md)
|
||||
|
||||
|
||||
## 变更日志
|
||||
|
||||
* 31/08/2022 EasyCV v0.6.0 版本发布。
|
||||
- 发布YOLOX-PAI，在轻量级模型中取得SOTA效果 (#154 #172 #174 )
|
||||
- 增加检测算法DINO (#144)
|
||||
- 增加Mask2Former算法 (#115)
|
||||
- Datahub新增imagenet1k, imagenet22k, coco, lvis, voc2012 数据的百度网盘链接，加速下载 (#145 )
|
||||
|
||||
|
||||
* 28/07/2022 EasyCV v0.5.0 版本发布。
|
||||
|
||||
* 23/06/2022 EasyCV v0.4.0 版本发布。
|
||||
|
||||
* 31/04/2022 EasyCV v0.3.0 版本发布。
|
||||
|
||||
* 2022/04/07 EasyCV v0.2.2 版本发布。
|
||||
|
||||
更多详细变更日志请参考[变更记录](docs/source/change_log.md)。
|
||||
|
||||
|
||||
## 开源许可证
|
||||
|
||||
本项目使用 [Apache 2.0 开源许可证](LICENSE). 项目内含有一些第三方依赖库源码，部分实现借鉴其他开源仓库，仓库名称和开源许可证说明请参考[NOTICE文件](NOTICE)。
|
||||
|
|
|
|||
Loading…
Reference in New Issue