diff --git a/README.md b/README.md index c8793a30a4..8b17475a54 100644 --- a/README.md +++ b/README.md @@ -7,6 +7,7 @@ English | [简体中文](README_CN.md) [![Version](https://img.shields.io/github/release/PaddlePaddle/PaddleSeg.svg)](https://github.com/PaddlePaddle/PaddleSeg/releases) ![python version](https://img.shields.io/badge/python-3.6+-orange.svg) ![support os](https://img.shields.io/badge/os-linux%2C%20win%2C%20mac-yellow.svg) + ## PaddleSeg has released the new version including the following features: * Our team won the AutoNUE@CVPR 2021 challenge, where the technical [report](https://bj.bcebos.com/paddleseg/docs/autonue21_presentation_PaddleSeg.pdf) and [source code](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.2/contrib/AutoNUE) are available. @@ -14,10 +15,30 @@ English | [简体中文](README_CN.md) * We introduced [Panoptic-DeepLab](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.2/contrib/PanopticDeepLab), which is a proposal-free algorithm for panoptic segmentation. * We provided an ultra-lightweight [portrait segmentation](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.2/contrib/HumanSeg) solution for the mobile devices and even the web -![demo](./docs/images/cityscapes.gif) +## PaddleSeg Introduction Welcome to PaddleSeg! PaddleSeg is an end-to-end image segmentation development kit developed based on [PaddlePaddle](https://www.paddlepaddle.org.cn), which covers a large number of high-quality segmentation models in different directions such as *high-performance* and *lightweight*. With the help of modular design, we provide two application methods: *Configuration Drive* and *API Calling*. So one can conveniently complete the entire image segmentation application from training to deployment through configuration calls or API calls. +* ### PaddleSeg provides four image segmentation capabilities: semantic segmentation, interactive segmentation, panoramic segmentation and Matting. + +
+ +
+ + +--------------- + + * ### PaddleSeg is widely used in autonomous driving, medical, quality inspection, inspection, entertainment and other scenarios. + +
+ +
+ + +--------------- + + + ## Core Features * **High Performance Model**: Based on the high-performance backbone trained by Baidu's self-developed [semi-supervised label knowledge distillation scheme (SSLD)](https://paddleclas.readthedocs.io/zh_CN/latest/advanced_tutorials/distillation/distillation.html#ssld), combined with the state of the art segmentation technology, we provides 50+ high-quality pre-training models, which are better than other open source implementations. @@ -31,38 +52,19 @@ Welcome to PaddleSeg! PaddleSeg is an end-to-end image segmentation development ## Technical Communication * If you find any problems or have a suggestion with PaddleSeg, please send us issues through [GitHub Issues](https://github.com/PaddlePaddle/PaddleSeg/issues). -* Welcome to Join PaddleSeg WeChat Group (left) and QQ Group (right) +* Welcome to Join PaddleSeg QQ Group +
+ +
+ +## Model Instraction + +[Model Zoo](./configs/) +
- +
-## Model Zoo - -|Model\Backbone|ResNet50|ResNet101|HRNetw18|HRNetw48| -|-|-|-|-|-| -|[ANN](./configs/ann)|✔|✔||| -|[BiSeNetv2](./configs/bisenet)|-|-|-|-| -|[DANet](./configs/danet)|✔|✔||| -|[Deeplabv3](./configs/deeplabv3)|✔|✔||| -|[Deeplabv3P](./configs/deeplabv3p)|✔|✔||| -|[Fast-SCNN](./configs/fastscnn)|-|-|-|-| -|[FCN](./configs/fcn)|||✔|✔| -|[GCNet](./configs/gcnet)|✔|✔||| -|[GSCNN](./configs/gscnn)|✔|✔||| -|[HarDNet](./configs/hardnet)|-|-|-|-| -|[OCRNet](./configs/ocrnet/)|||✔|✔| -|[PSPNet](./configs/pspnet)|✔|✔||| -|[U-Net](./configs/unet)|-|-|-|-| -|[U2-Net](./configs/u2net)|-|-|-|-| -|[Att U-Net](./configs/attention_unet)|-|-|-|-| -|[U-Net++](./configs/unet_plusplus)|-|-|-|-| -|[U-Net3+](./configs/unet_3plus)|-|-|-|-| -|[DecoupledSegNet](./configs/decoupled_segnet)|✔|✔||| -|[EMANet](./configs/emanet)|✔|✔|-|-| -|[ISANet](./configs/isanet)|✔|✔|-|-| -|[DNLNet](./configs/dnlnet)|✔|✔|-|-| -|[SFNet](./configs/sfnet)|✔|-|-|-| -|[PPSegLite](./configs/ppseg_lite)|-|-|-|-| ## Dataset diff --git a/README_CN.md b/README_CN.md index 7494e6b2d3..f812a7edef 100644 --- a/README_CN.md +++ b/README_CN.md @@ -22,7 +22,7 @@ PaddleSeg是基于飞桨[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的 * ### PaddleSeg提供了语义分割、交互式分割、全景分割、Matting四大图像分割能力。
- +
@@ -30,10 +30,10 @@ PaddleSeg是基于飞桨[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的 --------------- - * ### PaddleSeg被广泛的应用在自动驾驶、医疗、质检、巡检、娱乐等场景。 + * ### PaddleSeg被广泛地应用在自动驾驶、医疗、质检、巡检、娱乐等场景。
- +
---------------- @@ -65,9 +65,9 @@ PaddleSeg是基于飞桨[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的 ## 技术交流 * 如果你发现任何PaddleSeg存在的问题或者是建议, 欢迎通过[GitHub Issues](https://github.com/PaddlePaddle/PaddleSeg/issues)给我们提issues。 -* 欢迎加入PaddleSeg微信群（左侧）和QQ群（右侧） +* 欢迎加入PaddleSegQQ群
- +
## 模型说明 diff --git a/docs/images/ability_CH.gif b/docs/images/ability_CH.gif new file mode 100644 index 0000000000..282774e6e7 Binary files /dev/null and b/docs/images/ability_CH.gif differ diff --git a/docs/images/ability_EN.gif b/docs/images/ability_EN.gif new file mode 100644 index 0000000000..beeaa2dc3f Binary files /dev/null and b/docs/images/ability_EN.gif differ diff --git a/docs/images/application_CH.gif b/docs/images/application_CH.gif new file mode 100644 index 0000000000..b13c27db89 Binary files /dev/null and b/docs/images/application_CH.gif differ diff --git a/docs/images/application_EN.gif b/docs/images/application_EN.gif new file mode 100644 index 0000000000..70bd7ced94 Binary files /dev/null and b/docs/images/application_EN.gif differ diff --git a/docs/images/changjing.gif b/docs/images/changjing.gif deleted file mode 100644 index 46b1f06bb7..0000000000 Binary files a/docs/images/changjing.gif and /dev/null differ diff --git a/docs/images/nengli.gif b/docs/images/nengli.gif deleted file mode 100644 index c4f32e5bce..0000000000 Binary files a/docs/images/nengli.gif and /dev/null differ diff --git a/docs/images/seg_weichat.png b/docs/images/seg_weichat.png deleted file mode 100644 index 2319f1c6d3..0000000000 Binary files a/docs/images/seg_weichat.png and /dev/null differ diff --git a/docs/images/wechat_qq_711.png b/docs/images/wechat_qq_711.png deleted file mode 100644 index 6b8dcacfff..0000000000 Binary files a/docs/images/wechat_qq_711.png and /dev/null differ