Skip to content

Commit

Permalink
[Doc] add examples/vision/detection/fastestdet/README.md README_CN.md (
Browse files Browse the repository at this point in the history
…PaddlePaddle#1089)

add README.md README_CN.md
  • Loading branch information
GodIsBoom authored Jan 10, 2023
1 parent 7fdbedc commit 1039540
Show file tree
Hide file tree
Showing 2 changed files with 49 additions and 0 deletions.
25 changes: 25 additions & 0 deletions examples/vision/detection/fastestdet/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
English | [简体中文](README_CN.md)

# FastestDet Ready-to-deploy Model

- The deployment of the FastestDet model is based on [FastestDet](https://github.com/dog-qiuqiu/FastestDet.git) and [Pre-trained Model Based on COCO 2017](https://github.com/dog-qiuqiu/FastestDet.git)
- (1)The *.onnx provided by [Official Repository](https://github.com/dog-qiuqiu/FastestDet.git) can be deployed directly;
- (2)The FastestDet model trained by personal data should employ `test.py` in [FastestDet](https://github.com/dog-qiuqiu/FastestDet.git) to export the ONNX files for deployment.


## Download Pre-trained ONNX Model

For developers' testing, models exported by FastestDet are provided below. Developers can download them directly. (The accuracy in the following table is derived from the source official repository)
| Model | Size | Accuracy | Note |
|:---------------------------------------------------------------- |:----- |:----- |:---- |
| [FastestDet](https://bj.bcebos.com/paddlehub/fastdeploy/FastestDet.onnx) | 969KB | 25.3% | This model file is sourced from [FastestDet](https://github.com/dog-qiuqiu/FastestDet.git),BSD-3-Clause license |


## Detailed Deployment Documents

- [Python Deployment](python)
- [C++ Deployment](cpp)

## Release Note

- Document and code are based on [FastestDet](https://github.com/dog-qiuqiu/FastestDet.git)
24 changes: 24 additions & 0 deletions examples/vision/detection/fastestdet/README_CN.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
[English](README.md) | 简体中文
# FastestDet准备部署模型

- FastestDet部署模型实现来自[FastestDet](https://github.com/dog-qiuqiu/FastestDet.git),和[基于COCO的预训练模型](https://github.com/dog-qiuqiu/FastestDet.git)
- (1)[官方库](https://github.com/dog-qiuqiu/FastestDet.git)提供的*.onnx可直接进行部署;
- (2)开发者基于自己数据训练的 FastestDet模型,可使用[FastestDet](https://github.com/dog-qiuqiu/FastestDet.git)中的`test.py`导出ONNX文件后,完成部署。


## 下载预训练ONNX模型

为了方便开发者的测试,下面提供了FastestDet导出的模型,开发者可直接下载使用。(下表中模型的精度来源于源官方库)
| 模型 | 大小 | 精度 | 备注 |
|:---------------------------------------------------------------- |:----- |:----- |:---- |
| [FastestDet](https://bj.bcebos.com/paddlehub/fastdeploy/FastestDetn.onnx) | 969KB | 25.3% | 此模型文件来源于[FastestDet](https://github.com/dog-qiuqiu/FastestDet.git),BSD-3-Clause license |


## 详细部署文档

- [Python部署](python)
- [C++部署](cpp)

## 版本说明

- 本版本文档和代码基于[FastestDet](https://github.com/dog-qiuqiu/FastestDet.git) 编写

0 comments on commit 1039540

Please sign in to comment.