未验证 提交 0fe906d1 编写于 作者: W wangguanzhong 提交者: GitHub

update 2.1 readme (#3082)

* update 2.1 readme

* update en doc, test=document_fix
上级 2acad636
......@@ -3,6 +3,7 @@
# PaddleDetection
### PaddleDetection 2.0全面升级!目前默认使用动态图版本,静态图版本位于[static](./static)中
### 全新发布[关键点检测](configs/keypoint)和[多目标跟踪](configs/mot)能力!欢迎使用
### 超高性价比PPYOLO v2和1.3M超轻量PPYOLO tiny全新出炉![欢迎使用](configs/ppyolo/README_cn.md)
### Anchor Free SOTA模型PAFNet发布![欢迎使用](configs/ttfnet/README.md)
......@@ -20,6 +21,7 @@ PaddleDetection模块化地实现了多种主流目标检测算法,提供了
</div>
### 产品动态
- 2021.05.20: 发布release/2.1版本,新增[关键点检测](configs/keypoint),模型包括HigherHRNet,HRNet。新增[多目标跟踪](configs/mot)能力,模型包括DeepSORT,JDE,FairMOT。发布PPYOLO系列模型压缩模型,新增[ONNX模型导出教程](deploy/EXPORT_ONNX_MODEL.md),详情参考[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1)
- 2021.04.14: 发布release/2.0版本,PaddleDetection全面支持动态图,覆盖静态图模型算法,全面升级模型效果,同时发布[PP-YOLO v2, PPYOLO tiny](configs/ppyolo/README_cn.md)模型,增强版anchor free模型[PAFNet](configs/ttfnet/README.md),新增旋转框检测[S2ANet](configs/dota/README.md)模型,详情参考[PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0)
- 2021.02.07: 发布release/2.0-rc版本,PaddleDetection动态图试用版本,详情参考[PaddleDetection动态图](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0-rc)
......@@ -204,11 +206,12 @@ PaddleDetection模块化地实现了多种主流目标检测算法,提供了
- [推理部署](deploy/README.md)
- [模型导出教程](deploy/EXPORT_MODEL.md)
- [PaddleInference部署](deploy/README.md)
- [Paddle Inference部署](deploy/README.md)
- [Python端推理部署](deploy/python)
- [C++端推理部署](deploy/cpp)
- [PaddleLite部署](deploy/serving)
- [PaddleServing部署](deploy/lite)
- [Paddle-Lite部署](deploy/serving)
- [Paddle Serving部署](deploy/lite)
- [ONNX模型导出](deploy/EXPORT_ONNX_MODEL.md)
- [推理benchmark](deploy/BENCHMARK_INFER.md)
- 进阶开发
- [数据处理模块](docs/advanced_tutorials/READER.md)
......@@ -228,6 +231,13 @@ PaddleDetection模块化地实现了多种主流目标检测算法,提供了
- [SOLOv2](configs/solov2/README.md)
- 旋转框检测
- [S2ANet](configs/dota/README.md)
- [关键点检测](configs/keypoint)
- HigherHRNet
- HRNeet
- [多目标跟踪](configs/mot/README_cn.md)
- [DeepSORT](configs/mot/deepsort/README_cn.md)
- [JDE](configs/mot/jde/README_cn.md)
- [FairMOT](configs/mot/fairmot/README_cn.md)
- 垂类领域
- [行人检测](configs/pedestrian/README.md)
- [车辆检测](configs/vehicle/README.md)
......@@ -250,6 +260,8 @@ PaddleDetection模块化地实现了多种主流目标检测算法,提供了
## 版本更新
v2.1版本已经在`05/2021`发布,全新发布关键点检测和多目标跟踪能力,支持无标注框检测,发布PPYOLO系列模型压缩模型,新增ONNX模型导出教程,详细内容请参考[版本更新文档](docs/CHANGELOG.md)
v2.0版本已经在`04/2021`发布,全面支持动态图版本,新增支持BlazeFace, PSSDet等系列模型和大量骨干网络,发布PP-YOLO v2, PP-YOLO tiny和旋转框检测S2ANet模型。支持模型蒸馏、VisualDL,新增动态图预测部署benchmark,详细内容请参考[版本更新文档](docs/CHANGELOG.md)
......
......@@ -2,6 +2,8 @@ English | [简体中文](README_cn.md)
### PaddleDetection 2.0 is ready! Dygraph mode is set by default and static graph code base is [here](static)
### [Keypoint detection](configs/keypoint) and [Multi-Object Tracking](configs/mot) are released!
### Highly effective PPYOLO v2 and ultra lightweight PPYOLO tiny are released! [link](configs/ppyolo/README.md)
### SOTA Anchor Free model -- PAFNet is released! [link](configs/ttfnet/README.md)
......@@ -20,6 +22,7 @@ After a long time of industry practice polishing, PaddleDetection has had smooth
### Product news
- 2021.05.20: Release `release/2.1` version. Release [Keypoint Detection](configs/keypoint), including HigherHRNet and HRNet, [Multi-Object Tracking](configs/mot), including DeepSORT,JDE and FairMOT. Release model compression for PPYOLO series models.Update documents such as [EXPORT ONNX MODEL](deploy/EXPORT_ONNX_MODEL.md). Please refer to [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.1) for details.
- 2021.04.14: Release `release/2.0` version. Dygraph mode in PaddleDetection is fully supported. Cover all the algorithm of static graph and update the performance of mainstream detection models. Release [`PP-YOLO v2` and `PP-YOLO tiny`](configs/ppyolo/README.md), enhanced anchor free model [PAFNet](configs/ttfnet/README.md) and [`S2ANet`](configs/dota/README.md) which is aimed at rotation object detection.Please refer to [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0) for details.
- 2020.02.07: Release `release/2.0-rc` version, Please refer to [PaddleDetection](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.0-rc) for details.
......@@ -202,9 +205,8 @@ The relationship between COCO mAP and FPS on Tesla V100 of representative models
### Get Started
- [Installation guide](docs/tutorials/INSTALL_en.md)
- [Quick start on small dataset](docs/tutorials/QUICK_STARTED_en.md)
- [Prepare dataset](docs/tutorials/PrepareDataSet.md)
- [Train/Evaluation/Inference/Deploy](docs/tutorials/GETTING_STARTED_en.md)
- [Quick start on PaddleDetection](docs/tutorials/GETTING_STARTED_cn.md)
### Advanced Tutorials
......@@ -218,10 +220,12 @@ The relationship between COCO mAP and FPS on Tesla V100 of representative models
- Inference and deployment
- [Export model for inference](deploy/EXPORT_MODEL.md)
- [Paddle Inference](deploy/README.md)
- [Python inference](deploy/python)
- [C++ inference](deploy/cpp)
- [Serving](deploy/serving)
- [Paddle-Lite](deploy/lite)
- [Paddle Serving](deploy/serving)
- [Export ONNX model](deploy/EXPORT_ONNX_MODEL.md)
- [Inference benchmark](deploy/BENCHMARK_INFER.md)
- Advanced development
......@@ -257,6 +261,8 @@ The relationship between COCO mAP and FPS on Tesla V100 of representative models
## Updates
v2.1 was released at `05/2021`, Release Keypoint Detection and Multi-Object Tracking. Release model compression for PPYOLO series. Update documents such as export ONNX model. Please refer to [change log](docs/CHANGELOG.md) for details.
v2.0 was released at `04/2021`, fully support dygraph version, which add BlazeFace, PSS-Det and plenty backbones, release `PP-YOLOv2`, `PP-YOLO tiny` and `S2ANet`, support model distillation and VisualDL, add inference benchmark, etc. Please refer to [change log](docs/CHANGELOG.md) for details.
......
# PaddleDetection 预测部署
PaddleDetection提供了PaddleInference、PaddleServing、PaddleLite多种部署形式,支持服务端、移动端、嵌入式等多种平台,提供了完善的Python和C++部署方案。
PaddleDetection提供了Paddle Inference、Paddle Serving、Paddle-Lite多种部署形式,支持服务端、移动端、嵌入式等多种平台,提供了完善的Python和C++部署方案。
## PaddleDetection支持的部署形式说明
|形式|语言|教程|设备/平台|
|-|-|-|-|
|PaddleInference|Python|已完善|Linux(ARM\X86)、Windows
|PaddleInference|C++|已完善|Linux(ARM\X86)、Windows|
|PaddleServing|Python|已完善|Linux(ARM\X86)、Windows|
|PaddleLite|C++|已完善|Android、IOS、FPGA、RK...
|Paddle Inference|Python|已完善|Linux(ARM\X86)、Windows
|Paddle Inference|C++|已完善|Linux(ARM\X86)、Windows|
|Paddle Serving|Python|已完善|Linux(ARM\X86)、Windows|
|Paddle-Lite|C++|已完善|Android、IOS、FPGA、RK...
## 1.Paddle Inference部署
......
......@@ -21,6 +21,7 @@
- 文档:
- 更新快速开始,预测部署等教程文档
- 新增ONNX模型导出教程
- 新增移动端部署文档
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册