From 423376bc7d7fe323371b986d662a4c54992d870d Mon Sep 17 00:00:00 2001 From: KazusaW1999 <531336195@qq.com> Date: Tue, 24 Aug 2021 12:01:26 +0800 Subject: [PATCH 1/3] Adjust HumanSeg and related links. --- README.md | 2 +- README_CN.md | 2 +- contrib/{HumanSeg => PPSeg}/README.md | 0 contrib/{HumanSeg => PPSeg}/bg_replace.py | 0 ...8_small_v1_humanseg_192x192_mini_supervisely.yml | 0 contrib/{HumanSeg => PPSeg}/data/background.jpg | Bin contrib/{HumanSeg => PPSeg}/data/download_data.py | 0 contrib/{HumanSeg => PPSeg}/data/human_image.jpg | Bin contrib/{HumanSeg => PPSeg}/datasets/humanseg.py | 0 contrib/{HumanSeg => PPSeg}/deploy/infer.py | 0 .../export_model/download_export_model.py | 0 contrib/{HumanSeg => PPSeg}/predict.py | 0 .../pretrained_model/download_pretrained_model.py | 0 contrib/{HumanSeg => PPSeg}/scripts/__init__.py | 0 .../scripts/optic_flow_process.py | 0 contrib/{HumanSeg => PPSeg}/scripts/train.py | 0 contrib/{HumanSeg => PPSeg}/train.py | 0 contrib/{HumanSeg => PPSeg}/val.py | 0 18 files changed, 2 insertions(+), 2 deletions(-) rename contrib/{HumanSeg => PPSeg}/README.md (100%) rename contrib/{HumanSeg => PPSeg}/bg_replace.py (100%) rename contrib/{HumanSeg => PPSeg}/configs/fcn_hrnetw18_small_v1_humanseg_192x192_mini_supervisely.yml (100%) rename contrib/{HumanSeg => PPSeg}/data/background.jpg (100%) rename contrib/{HumanSeg => PPSeg}/data/download_data.py (100%) rename contrib/{HumanSeg => PPSeg}/data/human_image.jpg (100%) rename contrib/{HumanSeg => PPSeg}/datasets/humanseg.py (100%) rename contrib/{HumanSeg => PPSeg}/deploy/infer.py (100%) rename contrib/{HumanSeg => PPSeg}/export_model/download_export_model.py (100%) rename contrib/{HumanSeg => PPSeg}/predict.py (100%) rename contrib/{HumanSeg => PPSeg}/pretrained_model/download_pretrained_model.py (100%) rename contrib/{HumanSeg => PPSeg}/scripts/__init__.py (100%) rename contrib/{HumanSeg => PPSeg}/scripts/optic_flow_process.py (100%) rename contrib/{HumanSeg => PPSeg}/scripts/train.py (100%) rename contrib/{HumanSeg => PPSeg}/train.py (100%) rename contrib/{HumanSeg => PPSeg}/val.py (100%) diff --git a/README.md b/README.md index 946be847ff..071382e967 100644 --- a/README.md +++ b/README.md @@ -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/HumanSeg) solution for the mobile devices and even the web ## PaddleSeg Introduction diff --git a/README_CN.md b/README_CN.md index 923c0989d8..d74c9dbe89 100644 --- a/README_CN.md +++ b/README_CN.md @@ -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。 diff --git a/contrib/HumanSeg/README.md b/contrib/PPSeg/README.md similarity index 100% rename from contrib/HumanSeg/README.md rename to contrib/PPSeg/README.md diff --git a/contrib/HumanSeg/bg_replace.py b/contrib/PPSeg/bg_replace.py similarity index 100% rename from contrib/HumanSeg/bg_replace.py rename to contrib/PPSeg/bg_replace.py diff --git a/contrib/HumanSeg/configs/fcn_hrnetw18_small_v1_humanseg_192x192_mini_supervisely.yml b/contrib/PPSeg/configs/fcn_hrnetw18_small_v1_humanseg_192x192_mini_supervisely.yml similarity index 100% rename from contrib/HumanSeg/configs/fcn_hrnetw18_small_v1_humanseg_192x192_mini_supervisely.yml rename to contrib/PPSeg/configs/fcn_hrnetw18_small_v1_humanseg_192x192_mini_supervisely.yml diff --git a/contrib/HumanSeg/data/background.jpg b/contrib/PPSeg/data/background.jpg similarity index 100% rename from contrib/HumanSeg/data/background.jpg rename to contrib/PPSeg/data/background.jpg diff --git a/contrib/HumanSeg/data/download_data.py b/contrib/PPSeg/data/download_data.py similarity index 100% rename from contrib/HumanSeg/data/download_data.py rename to contrib/PPSeg/data/download_data.py diff --git a/contrib/HumanSeg/data/human_image.jpg b/contrib/PPSeg/data/human_image.jpg similarity index 100% rename from contrib/HumanSeg/data/human_image.jpg rename to contrib/PPSeg/data/human_image.jpg diff --git a/contrib/HumanSeg/datasets/humanseg.py b/contrib/PPSeg/datasets/humanseg.py similarity index 100% rename from contrib/HumanSeg/datasets/humanseg.py rename to contrib/PPSeg/datasets/humanseg.py diff --git a/contrib/HumanSeg/deploy/infer.py b/contrib/PPSeg/deploy/infer.py similarity index 100% rename from contrib/HumanSeg/deploy/infer.py rename to contrib/PPSeg/deploy/infer.py diff --git a/contrib/HumanSeg/export_model/download_export_model.py b/contrib/PPSeg/export_model/download_export_model.py similarity index 100% rename from contrib/HumanSeg/export_model/download_export_model.py rename to contrib/PPSeg/export_model/download_export_model.py diff --git a/contrib/HumanSeg/predict.py b/contrib/PPSeg/predict.py similarity index 100% rename from contrib/HumanSeg/predict.py rename to contrib/PPSeg/predict.py diff --git a/contrib/HumanSeg/pretrained_model/download_pretrained_model.py b/contrib/PPSeg/pretrained_model/download_pretrained_model.py similarity index 100% rename from contrib/HumanSeg/pretrained_model/download_pretrained_model.py rename to contrib/PPSeg/pretrained_model/download_pretrained_model.py diff --git a/contrib/HumanSeg/scripts/__init__.py b/contrib/PPSeg/scripts/__init__.py similarity index 100% rename from contrib/HumanSeg/scripts/__init__.py rename to contrib/PPSeg/scripts/__init__.py diff --git a/contrib/HumanSeg/scripts/optic_flow_process.py b/contrib/PPSeg/scripts/optic_flow_process.py similarity index 100% rename from contrib/HumanSeg/scripts/optic_flow_process.py rename to contrib/PPSeg/scripts/optic_flow_process.py diff --git a/contrib/HumanSeg/scripts/train.py b/contrib/PPSeg/scripts/train.py similarity index 100% rename from contrib/HumanSeg/scripts/train.py rename to contrib/PPSeg/scripts/train.py diff --git a/contrib/HumanSeg/train.py b/contrib/PPSeg/train.py similarity index 100% rename from contrib/HumanSeg/train.py rename to contrib/PPSeg/train.py diff --git a/contrib/HumanSeg/val.py b/contrib/PPSeg/val.py similarity index 100% rename from contrib/HumanSeg/val.py rename to contrib/PPSeg/val.py From 652ae724519dd746ad95983127bbf286480a30c1 Mon Sep 17 00:00:00 2001 From: KazusaW1999 <85934066+KazusaW1999@users.noreply.github.com> Date: Tue, 24 Aug 2021 12:58:24 +0800 Subject: [PATCH 2/3] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 071382e967..54e618c80b 100644 --- a/README.md +++ b/README.md @@ -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](./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 From ba6af98b61029e792178785fea68920ebd75fd22 Mon Sep 17 00:00:00 2001 From: KazusaW1999 <531336195@qq.com> Date: Wed, 25 Aug 2021 11:31:08 +0800 Subject: [PATCH 3/3] Modify missing links. --- README.md | 4 ++-- README_CN.md | 2 +- configs/ppseg_lite/README.md | 2 +- contrib/PPSeg/README.md | 4 ++-- contrib/PPSeg/bg_replace.py | 2 +- deploy/lite/README.md | 2 +- docs/release_notes.md | 2 +- docs/release_notes_cn.md | 2 +- docs/solution/human/human.md | 2 +- 9 files changed, 11 insertions(+), 11 deletions(-) diff --git a/README.md b/README.md index 071382e967..910400ed89 100644 --- a/README.md +++ b/README.md @@ -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](./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 @@ -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) diff --git a/README_CN.md b/README_CN.md index d74c9dbe89..8a9efcc2b0 100644 --- a/README_CN.md +++ b/README_CN.md @@ -121,7 +121,7 @@ PaddleSeg是基于飞桨[PaddlePaddle](https://www.paddlepaddle.org.cn)开发的 ## 实践案例 -- [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) diff --git a/configs/ppseg_lite/README.md b/configs/ppseg_lite/README.md index faec11fc5a..3072259301 100644 --- a/configs/ppseg_lite/README.md +++ b/configs/ppseg_lite/README.md @@ -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). diff --git a/contrib/PPSeg/README.md b/contrib/PPSeg/README.md index 585e600c84..83151dd671 100644 --- a/contrib/PPSeg/README.md +++ b/contrib/PPSeg/README.md @@ -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 diff --git a/contrib/PPSeg/bg_replace.py b/contrib/PPSeg/bg_replace.py index a21cd6d9bd..383fd5d1aa 100644 --- a/contrib/PPSeg/bg_replace.py +++ b/contrib/PPSeg/bg_replace.py @@ -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", diff --git a/deploy/lite/README.md b/deploy/lite/README.md index 08bbc26ad2..30f961fe29 100644 --- a/deploy/lite/README.md +++ b/deploy/lite/README.md @@ -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 diff --git a/docs/release_notes.md b/docs/release_notes.md index 1f22e10e06..fa35533cad 100644 --- a/docs/release_notes.md +++ b/docs/release_notes.md @@ -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 diff --git a/docs/release_notes_cn.md b/docs/release_notes_cn.md index f6636487b4..772c4c892a 100644 --- a/docs/release_notes_cn.md +++ b/docs/release_notes_cn.md @@ -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 diff --git a/docs/solution/human/human.md b/docs/solution/human/human.md index 18aa09c582..514fab6abe 100644 --- a/docs/solution/human/human.md +++ b/docs/solution/human/human.md @@ -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)