Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adjust HumanSeg's name and related links. #1279

Merged
merged 5 commits into from
Aug 25, 2021
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ English | [简体中文](README_CN.md)
* 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.
* We released an efficient interactive annotation tool for image segmentation, named [EISeg](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.2/contrib/EISeg).
* 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
* We provided an ultra-lightweight [portrait segmentation](./contrib/PPSeg) solution for the mobile devices and even the web

## PaddleSeg Introduction

Expand Down Expand Up @@ -149,7 +149,7 @@ python train.py --config configs/quick_start/bisenet_optic_disc_512x512_1k.yml

## Practical Cases

* [HumanSeg](./contrib/HumanSeg)
* [PPSeg](./contrib/PPSeg)
* [Cityscapes SOTA](./contrib/CityscapesSOTA)
* [Panoptic Segmentation](./contrib/PanopticDeepLab)

Expand Down
4 changes: 2 additions & 2 deletions README_CN.md
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@
* PaddleSeg团队在CVPR2021 AutoNUE语义分割赛道中获得冠军! 已发布[演讲报告](https://bj.bcebos.com/paddleseg/docs/autonue21_presentation_PaddleSeg.pdf)和[源代码](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.2/contrib/AutoNUE)。
* 发布了交互式分割的智能标注工具 [EISeg](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.2/contrib/EISeg)。极大的提升了标注效率;
* 开源了全景分割算法[Panoptic-DeepLab](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.2/contrib/PanopticDeepLab)丰富了模型种类;
* 全新升级了[人像分割](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.2/contrib/HumanSeg)功能,提供了web端超轻量模型部署方案
* 全新升级了[人像分割](./contrib/PPSeg)功能,提供了web端超轻量模型部署方案

## PaddleSeg介绍
PaddleSeg是基于飞桨[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的端到端图像分割开发套件,涵盖了**高精度**和**轻量级**等不同方向的大量高质量分割模型。通过模块化的设计,提供了**配置化驱动**和**API调用**两种应用方式,帮助开发者更便捷地完成从训练到部署的全流程图像分割应用。
Expand Down Expand Up @@ -121,7 +121,7 @@ PaddleSeg是基于飞桨[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的

## 实践案例 <img src="./docs/images/anli.png" width="20"/>

- [人像分割](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.1/contrib/HumanSeg)
- [人像分割](./contrib/PPSeg)
- [医疗图像](./docs/solution/medical/medical.md)
- [遥感分割](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.1/contrib/remote_sensing)
- [全景分割](./contrib/PanopticDeepLab)
Expand Down
2 changes: 1 addition & 1 deletion configs/ppseg_lite/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,4 +3,4 @@
自研超轻量级模型,适用于Web端或移动端实时分割场景。

## Performance
Refer to [人像分割PPSeg](../../contrib/HumanSeg).
Refer to [人像分割PPSeg](../../contrib/PPSeg).
4 changes: 2 additions & 2 deletions contrib/HumanSeg/README.md → contrib/PPSeg/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -90,9 +90,9 @@ git clone https://github.com/PaddlePaddle/PaddleSeg
```

## 快速体验
以下所有命令均在`PaddleSeg/contrib/HumanSeg`目录下执行。
以下所有命令均在`PaddleSeg/contrib/PPSeg`目录下执行。
```shell
cd PaddleSeg/contrib/HumanSeg
cd PaddleSeg/contrib/PPSeg
```

### 下载Inference Model
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -25,7 +25,7 @@


def parse_args():
parser = argparse.ArgumentParser(description='HumanSeg inference for video')
parser = argparse.ArgumentParser(description='PPSeg inference for video')
parser.add_argument(
"--config",
dest="cfg",
Expand Down
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
2 changes: 1 addition & 1 deletion deploy/lite/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ Paddle-Lite的编译目前支持Docker,Linux和Mac OS开发环境,建议使
准备好上述文件,即可参考[java_api](https://paddle-lite.readthedocs.io/zh/release-v2.8/api_reference/java_api_doc.html)在安卓端进行推理。具体使用预测库的方法可参考[Paddle-Lite-Demo](https://github.com/PaddlePaddle/Paddle-Lite-Demo)中更新预测库部分的文档。

### 3.2 模型导出
此demo的人像分割模型为基于HRNet w18 small v1的humanseg模型([下载链接](https://bj.bcebos.com/paddleseg/deploy/lite/android/hrnet_w18_small.tar.gz)),更多的分割模型导出可参考:[模型导出](../../docs/model_export.md)
此demo的人像分割模型为基于HRNet w18 small v1的ppseg模型([下载链接](https://bj.bcebos.com/paddleseg/deploy/lite/android/hrnet_w18_small.tar.gz)),更多的分割模型导出可参考:[模型导出](../../docs/model_export.md)

### 3.3 模型转换

Expand Down
2 changes: 1 addition & 1 deletion docs/release_notes.md
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ English | [简体中文](release_notes_cn.md)
* 2020.05.12

**`v0.5.0`**
* 全面升级[HumanSeg人像分割模型](../contrib/HumanSeg),新增超轻量级人像分割模型HumanSeg-lite支持移动端实时人像分割处理,并提供基于光流的视频分割后处理提升分割流畅性。
* 全面升级[HumanSeg人像分割模型](../contrib/PPSeg),新增超轻量级人像分割模型HumanSeg-lite支持移动端实时人像分割处理,并提供基于光流的视频分割后处理提升分割流畅性。
* 新增[气象遥感分割方案](../contrib/RemoteSensing),支持积雪识别、云检测等气象遥感场景。
* 新增[Lovasz Loss](lovasz_loss.md),解决数据类别不均衡问题。
* 使用VisualDL 2.0作为训练可视化工具
Expand Down
2 changes: 1 addition & 1 deletion docs/release_notes_cn.md
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@
* 2020.05.12

**`v0.5.0`**
* 全面升级[HumanSeg人像分割模型](../contrib/HumanSeg),新增超轻量级人像分割模型HumanSeg-lite支持移动端实时人像分割处理,并提供基于光流的视频分割后处理提升分割流畅性。
* 全面升级[HumanSeg人像分割模型](../contrib/PPSeg),新增超轻量级人像分割模型HumanSeg-lite支持移动端实时人像分割处理,并提供基于光流的视频分割后处理提升分割流畅性。
* 新增[气象遥感分割方案](../contrib/RemoteSensing),支持积雪识别、云检测等气象遥感场景。
* 新增[Lovasz Loss](lovasz_loss.md),解决数据类别不均衡问题。
* 使用VisualDL 2.0作为训练可视化工具
Expand Down
2 changes: 1 addition & 1 deletion docs/solution/human/human.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# 人像分割HumanSeg

本教程基于PaddleSeg提供高精度人像分割模型,从训练到部署的全流程应用指南,以及视频流人像分割、背景替换的实际效果体验。最新发布超轻量级人像分割模型,支持Web端、移动端场景的实时分割。[代码链接](https://github.com/PaddlePaddle/PaddleSeg/tree/release/2.1/contrib/HumanSeg)
本教程基于PaddleSeg提供高精度人像分割模型,从训练到部署的全流程应用指南,以及视频流人像分割、背景替换的实际效果体验。最新发布超轻量级人像分割模型,支持Web端、移动端场景的实时分割。[代码链接](../../../contrib/PPSeg)

- [人像分割模型](#人像分割模型)
- [安装](#安装)
Expand Down