mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-25 17:40:35 +08:00
[Doc]Add English version of documents in examples (#1070)
* Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update README_EN.md * Rename README_EN.md to README_CN.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update README_EN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update README_EN.md * Rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update README.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README_CN.md * Update README.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README.md * Update and rename README_CN.md to README_EN.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update and rename README_EN.md to README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README.md * Update README_CN.md * Update README_CN.md * Update README.md * Update export.md * Create export_cn.md * Update README.md * Create README_CN.md * Update README.md * Create README_CN.md
This commit is contained in:
Hu Chuqi
@@ -1,37 +1,39 @@
|
||||
# PP-TinyPose 模型部署
|
||||
English | [简体中文](README_CN.md)
|
||||
# PP-TinyPose Model Deployment
|
||||
|
||||
## 模型版本说明
|
||||
## Model Description
|
||||
|
||||
- [PaddleDetection release/2.5](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5)
|
||||
|
||||
目前FastDeploy支持如下模型的部署
|
||||
Now FastDeploy supports the deployment of the following models
|
||||
|
||||
- [PP-TinyPose系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/tiny_pose/README.md)
|
||||
- [PP-TinyPose models](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/tiny_pose/README.md)
|
||||
|
||||
## 准备PP-TinyPose部署模型
|
||||
## Prepare PP-TinyPose Deployment Model
|
||||
|
||||
PP-TinyPose模型导出，请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/deploy/EXPORT_MODEL.md)
|
||||
Export the PP-TinyPose model. Please refer to [Model Export](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/deploy/EXPORT_MODEL.md)
|
||||
|
||||
**注意**:PP-TinyPose导出的模型包含`model.pdmodel`、`model.pdiparams`和`infer_cfg.yml`三个文件，FastDeploy会从yaml文件中获取模型在推理时需要的预处理信息。
|
||||
**Attention**: The exported PP-TinyPose model contains three files, including `model.pdmodel`、`model.pdiparams` and `infer_cfg.yml`. FastDeploy will get the pre-processing information for inference from yaml files.
|
||||
|
||||
|
||||
## 下载预训练模型
|
||||
## Download Pre-trained Model
|
||||
|
||||
为了方便开发者的测试，下面提供了PP-TinyPose导出的部分模型，开发者可直接下载使用。
|
||||
For developers' testing, part of the PP-TinyPose exported models are provided below. Developers can download and use them directly.
|
||||
|
||||
| 模型 | 参数文件大小 |输入Shape | AP(业务数据集) | AP(COCO Val) | FLOPS | 单人推理耗时 (FP32) | 单人推理耗时（FP16) |
|
||||
| Model | Parameter File Size | Input Shape | AP(Service Data set) | AP(COCO Val) | FLOPS | Single/Multi-person Inference Time (FP32) | Single/Multi-person Inference Time（FP16) |
|
||||
|:---------------------------------------------------------------- |:----- |:----- | :----- | :----- | :----- | :----- | :----- |
|
||||
| [PP-TinyPose-128x96](https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_128x96_infer.tgz) | 5.3MB | 128x96 | 84.3% | 58.4% | 81.56 M | 4.57ms | 3.27ms |
|
||||
| [PP-TinyPose-256x192](https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz) | 5.3M | 256x96 | 91.0% | 68.3% | 326.24M | 14.07ms | 8.33ms |
|
||||
|
||||
**说明**
|
||||
- 关键点检测模型使用`COCO train2017`和`AI Challenger trainset`作为训练集。使用`COCO person keypoints val2017`作为测试集。
|
||||
- 关键点检测模型的精度指标所依赖的检测框为ground truth标注得到。
|
||||
- 推理速度测试环境为 Qualcomm Snapdragon 865，采用arm8下4线程推理得到。
|
||||
**Note**
|
||||
- The keypoint detection model uses `COCO train2017` and `AI Challenger trainset` as the training sets and `COCO person keypoints val2017` as the test set.
|
||||
- The detection frame, through which we get the accuracy of the keypoint detection model, is obtained from the ground truth annotation.
|
||||
- The speed test environment is Qualcomm Snapdragon 865 with 4-thread inference under arm8.
|
||||
|
||||
更多信息请参考：[PP-TinyPose 官方文档](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/tiny_pose/README.md)
|
||||
|
||||
## 详细部署文档
|
||||
For more information: refer to [PP-TinyPose official document](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/tiny_pose/README.md)
|
||||
|
||||
- [Python部署](python)
|
||||
- [C++部署](cpp)
|
||||
## Detailed Deployment Tutorials
|
||||
|
||||
- [Python Deployment](python)
|
||||
- [C++ Deployment](cpp)
|
||||
|
||||
38
examples/vision/keypointdetection/tiny_pose/README_CN.md
Normal file
38
examples/vision/keypointdetection/tiny_pose/README_CN.md
Normal file
@@ -0,0 +1,38 @@
|
||||
[English](README.md) | 简体中文
|
||||
# PP-TinyPose 模型部署
|
||||
|
||||
## 模型版本说明
|
||||
|
||||
- [PaddleDetection release/2.5](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5)
|
||||
|
||||
目前FastDeploy支持如下模型的部署
|
||||
|
||||
- [PP-TinyPose系列模型](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/tiny_pose/README.md)
|
||||
|
||||
## 准备PP-TinyPose部署模型
|
||||
|
||||
PP-TinyPose模型导出，请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/deploy/EXPORT_MODEL.md)
|
||||
|
||||
**注意**:PP-TinyPose导出的模型包含`model.pdmodel`、`model.pdiparams`和`infer_cfg.yml`三个文件，FastDeploy会从yaml文件中获取模型在推理时需要的预处理信息。
|
||||
|
||||
|
||||
## 下载预训练模型
|
||||
|
||||
为了方便开发者的测试，下面提供了PP-TinyPose导出的部分模型，开发者可直接下载使用。
|
||||
|
||||
| 模型 | 参数文件大小 |输入Shape | AP(业务数据集) | AP(COCO Val) | FLOPS | 单人推理耗时 (FP32) | 单人推理耗时（FP16) |
|
||||
|:---------------------------------------------------------------- |:----- |:----- | :----- | :----- | :----- | :----- | :----- |
|
||||
| [PP-TinyPose-128x96](https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_128x96_infer.tgz) | 5.3MB | 128x96 | 84.3% | 58.4% | 81.56 M | 4.57ms | 3.27ms |
|
||||
| [PP-TinyPose-256x192](https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz) | 5.3M | 256x96 | 91.0% | 68.3% | 326.24M | 14.07ms | 8.33ms |
|
||||
|
||||
**说明**
|
||||
- 关键点检测模型使用`COCO train2017`和`AI Challenger trainset`作为训练集。使用`COCO person keypoints val2017`作为测试集。
|
||||
- 关键点检测模型的精度指标所依赖的检测框为ground truth标注得到。
|
||||
- 推理速度测试环境为 Qualcomm Snapdragon 865，采用arm8下4线程推理得到。
|
||||
|
||||
更多信息请参考：[PP-TinyPose 官方文档](https://github.com/PaddlePaddle/PaddleDetection/tree/release/2.5/configs/keypoint/tiny_pose/README.md)
|
||||
|
||||
## 详细部署文档
|
||||
|
||||
- [Python部署](python)
|
||||
- [C++部署](cpp)
|
||||
@@ -1,52 +1,53 @@
|
||||
# PP-TinyPose C++部署示例
|
||||
English | [简体中文](README_CN.md)
|
||||
# PP-TinyPose C++ Deployment Example
|
||||
|
||||
本目录下提供`pptinypose_infer.cc`快速完成PP-TinyPose在CPU/GPU，以及GPU上通过TensorRT加速部署的`单图单人关键点检测`示例
|
||||
>> **注意**: PP-Tinypose单模型目前只支持单图单人关键点检测，因此输入的图片应只包含一个人或者进行过裁剪的图像。多人关键点检测请参考[PP-TinyPose Pipeline](../../det_keypoint_unite/cpp/README.md)
|
||||
This directory provides the `Multi-person keypoint detection in a single image` example that `pptinypose_infer.cc` fast finishes the deployment of PP-TinyPose on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
|
||||
>> **Attention**: PP-Tinypose single model currently supports single-person keypoint detection in a single image. Therefore, the input image should contain one person only or should be cropped. For multi-person keypoint detection, refer to [PP-TinyPose Pipeline](../../det_keypoint_unite/cpp/README.md)
|
||||
|
||||
在部署前，需确认以下两个步骤
|
||||
Before deployment, two steps require confirmation
|
||||
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
|
||||
|
||||
以Linux上推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
|
||||
Taking the inference on Linux as an example, the compilation test can be completed by executing the following command in this directory. FastDeploy version 0.7.0 or above (x.x.x>=0.7.0) is required to support this model.
|
||||
|
||||
```bash
|
||||
mkdir build
|
||||
cd build
|
||||
# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
|
||||
# Download the FastDeploy precompiled library. Users can choose your appropriate version in the `FastDeploy Precompiled Library` mentioned above
|
||||
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
|
||||
tar xvf fastdeploy-linux-x64-x.x.x.tgz
|
||||
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
|
||||
make -j
|
||||
|
||||
# 下载PP-TinyPose模型文件和测试图片
|
||||
# Download PP-TinyPose model files and test images
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz
|
||||
tar -xvf PP_TinyPose_256x192_infer.tgz
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/hrnet_demo.jpg
|
||||
|
||||
|
||||
# CPU推理
|
||||
# CPU inference
|
||||
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 0
|
||||
# GPU推理
|
||||
# GPU inference
|
||||
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 1
|
||||
# GPU上TensorRT推理
|
||||
# TensorRT inference on GPU
|
||||
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 2
|
||||
# 昆仑芯XPU推理
|
||||
# KunlunXin XPU inference
|
||||
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 3
|
||||
```
|
||||
|
||||
运行完成可视化结果如下图所示
|
||||
The visualized result after running is as follows
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/16222477/196386764-dd51ad56-c410-4c54-9580-643f282f5a83.jpeg", width=359px, height=423px />
|
||||
</div>
|
||||
|
||||
以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
|
||||
- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
The above command works for Linux or MacOS. For SDK use-pattern in Windows, refer to:
|
||||
- [How to use FastDeploy C++ SDK in Windows](../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
|
||||
## PP-TinyPose C++接口
|
||||
## PP-TinyPose C++ Interface
|
||||
|
||||
### PP-TinyPose类
|
||||
### PP-TinyPose Class
|
||||
|
||||
```c++
|
||||
fastdeploy::vision::keypointdetection::PPTinyPose(
|
||||
@@ -57,34 +58,34 @@ fastdeploy::vision::keypointdetection::PPTinyPose(
|
||||
const ModelFormat& model_format = ModelFormat::PADDLE)
|
||||
```
|
||||
|
||||
PPTinyPose模型加载和初始化，其中model_file为导出的Paddle模型格式。
|
||||
PPTinyPose model loading and initialization, among which model_file is the exported Paddle model format.
|
||||
|
||||
**参数**
|
||||
**Parameter**
|
||||
|
||||
> * **model_file**(str): 模型文件路径
|
||||
> * **params_file**(str): 参数文件路径
|
||||
> * **config_file**(str): 推理部署配置文件
|
||||
> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
|
||||
> * **model_format**(ModelFormat): 模型格式，默认为Paddle格式
|
||||
> * **model_file**(str): Model file path
|
||||
> * **params_file**(str): Parameter file path
|
||||
> * **config_file**(str): Inference deployment configuration file
|
||||
> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
|
||||
> * **model_format**(ModelFormat): Model format. Paddle format by default
|
||||
|
||||
#### Predict函数
|
||||
#### Predict function
|
||||
|
||||
> ```c++
|
||||
> PPTinyPose::Predict(cv::Mat* im, KeyPointDetectionResult* result)
|
||||
> ```
|
||||
>
|
||||
> 模型预测接口，输入图像直接输出关键点检测结果。
|
||||
> Model prediction interface. Input images and output keypoint detection results.
|
||||
>
|
||||
> **参数**
|
||||
> **Parameter**
|
||||
>
|
||||
> > * **im**: 输入图像，注意需为HWC，BGR格式
|
||||
> > * **result**: 关键点检测结果，包括关键点的坐标以及关键点对应的概率值, KeyPointDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
> > * **im**: Input images in HWC or BGR format
|
||||
> > * **result**: Keypoint detection results, including coordinates and the corresponding probability value. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for the description of KeyPointDetectionResult
|
||||
|
||||
### 类成员属性
|
||||
#### 后处理参数
|
||||
> > * **use_dark**(bool): 是否使用DARK进行后处理[参考论文](https://arxiv.org/abs/1910.06278)
|
||||
### Class Member Property
|
||||
#### Post-processing Parameter
|
||||
> > * **use_dark**(bool): Whether to use DARK for post-processing. Refer to [Reference Paper](https://arxiv.org/abs/1910.06278)
|
||||
|
||||
- [模型介绍](../../)
|
||||
- [Python部署](../python)
|
||||
- [视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
- [Model Description](../../)
|
||||
- [Python Deployment](../python)
|
||||
- [Vision Model Prediction Results](../../../../../docs/api/vision_results/)
|
||||
- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
|
||||
91
examples/vision/keypointdetection/tiny_pose/cpp/README_CN.md
Normal file
91
examples/vision/keypointdetection/tiny_pose/cpp/README_CN.md
Normal file
@@ -0,0 +1,91 @@
|
||||
[English](README.md) | 简体中文
|
||||
# PP-TinyPose C++部署示例
|
||||
|
||||
本目录下提供`pptinypose_infer.cc`快速完成PP-TinyPose在CPU/GPU，以及GPU上通过TensorRT加速部署的`单图单人关键点检测`示例
|
||||
>> **注意**: PP-Tinypose单模型目前只支持单图单人关键点检测，因此输入的图片应只包含一个人或者进行过裁剪的图像。多人关键点检测请参考[PP-TinyPose Pipeline](../../det_keypoint_unite/cpp/README.md)
|
||||
|
||||
在部署前，需确认以下两个步骤
|
||||
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
|
||||
|
||||
以Linux上推理为例，在本目录执行如下命令即可完成编译测试，支持此模型需保证FastDeploy版本0.7.0以上(x.x.x>=0.7.0)
|
||||
|
||||
```bash
|
||||
mkdir build
|
||||
cd build
|
||||
# 下载FastDeploy预编译库，用户可在上文提到的`FastDeploy预编译库`中自行选择合适的版本使用
|
||||
wget https://bj.bcebos.com/fastdeploy/release/cpp/fastdeploy-linux-x64-x.x.x.tgz
|
||||
tar xvf fastdeploy-linux-x64-x.x.x.tgz
|
||||
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-x.x.x
|
||||
make -j
|
||||
|
||||
# 下载PP-TinyPose模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz
|
||||
tar -xvf PP_TinyPose_256x192_infer.tgz
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/hrnet_demo.jpg
|
||||
|
||||
|
||||
# CPU推理
|
||||
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 0
|
||||
# GPU推理
|
||||
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 1
|
||||
# GPU上TensorRT推理
|
||||
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 2
|
||||
# 昆仑芯XPU推理
|
||||
./infer_tinypose_demo PP_TinyPose_256x192_infer hrnet_demo.jpg 3
|
||||
```
|
||||
|
||||
运行完成可视化结果如下图所示
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/16222477/196386764-dd51ad56-c410-4c54-9580-643f282f5a83.jpeg", width=359px, height=423px />
|
||||
</div>
|
||||
|
||||
以上命令只适用于Linux或MacOS, Windows下SDK的使用方式请参考:
|
||||
- [如何在Windows中使用FastDeploy C++ SDK](../../../../../docs/cn/faq/use_sdk_on_windows.md)
|
||||
|
||||
## PP-TinyPose C++接口
|
||||
|
||||
### PP-TinyPose类
|
||||
|
||||
```c++
|
||||
fastdeploy::vision::keypointdetection::PPTinyPose(
|
||||
const string& model_file,
|
||||
const string& params_file = "",
|
||||
const string& config_file,
|
||||
const RuntimeOption& runtime_option = RuntimeOption(),
|
||||
const ModelFormat& model_format = ModelFormat::PADDLE)
|
||||
```
|
||||
|
||||
PPTinyPose模型加载和初始化，其中model_file为导出的Paddle模型格式。
|
||||
|
||||
**参数**
|
||||
|
||||
> * **model_file**(str): 模型文件路径
|
||||
> * **params_file**(str): 参数文件路径
|
||||
> * **config_file**(str): 推理部署配置文件
|
||||
> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
|
||||
> * **model_format**(ModelFormat): 模型格式，默认为Paddle格式
|
||||
|
||||
#### Predict函数
|
||||
|
||||
> ```c++
|
||||
> PPTinyPose::Predict(cv::Mat* im, KeyPointDetectionResult* result)
|
||||
> ```
|
||||
>
|
||||
> 模型预测接口，输入图像直接输出关键点检测结果。
|
||||
>
|
||||
> **参数**
|
||||
>
|
||||
> > * **im**: 输入图像，注意需为HWC，BGR格式
|
||||
> > * **result**: 关键点检测结果，包括关键点的坐标以及关键点对应的概率值, KeyPointDetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
|
||||
### 类成员属性
|
||||
#### 后处理参数
|
||||
> > * **use_dark**(bool): 是否使用DARK进行后处理[参考论文](https://arxiv.org/abs/1910.06278)
|
||||
|
||||
- [模型介绍](../../)
|
||||
- [Python部署](../python)
|
||||
- [视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
@@ -1,81 +1,81 @@
|
||||
# PP-TinyPose Python部署示例
|
||||
English | [简体中文](README_CN.md)
|
||||
# PP-TinyPose Python Deployment Example
|
||||
|
||||
在部署前，需确认以下两个步骤
|
||||
Before deployment, two steps require confirmation
|
||||
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. Download the precompiled deployment library and samples code according to your development environment. Refer to [FastDeploy Precompiled Library](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
|
||||
本目录下提供`pptinypose_infer.py`快速完成PP-TinyPose在CPU/GPU，以及GPU上通过TensorRT加速部署的`单图单人关键点检测`示例。执行如下脚本即可完成
|
||||
|
||||
>> **注意**: PP-Tinypose单模型目前只支持单图单人关键点检测，因此输入的图片应只包含一个人或者进行过裁剪的图像。多人关键点检测请参考[PP-TinyPose Pipeline](../../det_keypoint_unite/python/README.md)
|
||||
This directory provides the `Multi-person keypoint detection in a single image` example that `pptinypose_infer.py` fast finishes the deployment of PP-TinyPose on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
|
||||
>> **Attention**: single model currently only supports single-person keypoint detection in a single image. Therefore, the input image should contain one person only or should be cropped. For multi-person keypoint detection, refer to [PP-TinyPose Pipeline](../../det_keypoint_unite/python/README.md)
|
||||
|
||||
```bash
|
||||
#下载部署示例代码
|
||||
# Download the example code for deployment
|
||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||
cd FastDeploy/examples/vision/keypointdetection/tiny_pose/python
|
||||
|
||||
# 下载PP-TinyPose模型文件和测试图片
|
||||
# Download PP-TinyPose model files and test images
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz
|
||||
tar -xvf PP_TinyPose_256x192_infer.tgz
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/hrnet_demo.jpg
|
||||
|
||||
# CPU推理
|
||||
# CPU inference
|
||||
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device cpu
|
||||
# GPU推理
|
||||
# GPU inference
|
||||
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device gpu
|
||||
# GPU上使用TensorRT推理 （注意：TensorRT推理第一次运行，有序列化模型的操作，有一定耗时，需要耐心等待）
|
||||
# TensorRT inference on GPU（Attention: It is somewhat time-consuming for the operation of model serialization when running TensorRT inference for the first time. Please be patient.）
|
||||
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device gpu --use_trt True
|
||||
# 昆仑芯XPU推理
|
||||
# KunlunXin XPU inference
|
||||
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device kunlunxin
|
||||
```
|
||||
|
||||
运行完成可视化结果如下图所示
|
||||
The visualized result after running is as follows
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/16222477/196386764-dd51ad56-c410-4c54-9580-643f282f5a83.jpeg", width=359px, height=423px />
|
||||
</div>
|
||||
|
||||
## PP-TinyPose Python接口
|
||||
## PP-TinyPose Python Interface
|
||||
|
||||
```python
|
||||
fd.vision.keypointdetection.PPTinyPose(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
|
||||
```
|
||||
|
||||
PP-TinyPose模型加载和初始化，其中model_file, params_file以及config_file为训练模型导出的Paddle inference文件，具体请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/deploy/EXPORT_MODEL.md)
|
||||
PP-TinyPose model loading and initialization, among which model_file, params_file, and config_file are the Paddle inference files exported from the training model. Refer to [Model Export](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/deploy/EXPORT_MODEL.md) for more information
|
||||
|
||||
**参数**
|
||||
**Parameter**
|
||||
|
||||
> * **model_file**(str): 模型文件路径
|
||||
> * **params_file**(str): 参数文件路径
|
||||
> * **config_file**(str): 推理部署配置文件
|
||||
> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
|
||||
> * **model_format**(ModelFormat): 模型格式，默认为Paddle格式
|
||||
> * **model_file**(str): Model file path
|
||||
> * **params_file**(str): Parameter file path
|
||||
> * **config_file**(str): Inference deployment configuration file
|
||||
> * **runtime_option**(RuntimeOption): Backend inference configuration. None by default, which is the default configuration
|
||||
> * **model_format**(ModelFormat): Model format. Paddle format by default
|
||||
|
||||
### predict函数
|
||||
### predict function
|
||||
|
||||
> ```python
|
||||
> PPTinyPose.predict(input_image)
|
||||
> ```
|
||||
>
|
||||
> 模型预测结口，输入图像直接输出检测结果。
|
||||
> Model prediction interface. Input images and output detection results.
|
||||
>
|
||||
> **参数**
|
||||
> **Parameter**
|
||||
>
|
||||
> > * **input_image**(np.ndarray): 输入数据，注意需为HWC，BGR格式
|
||||
> > * **input_image**(np.ndarray): Input data in HWC or BGR format
|
||||
|
||||
> **返回**
|
||||
> **Return**
|
||||
>
|
||||
> > 返回`fastdeploy.vision.KeyPointDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
> > Return `fastdeploy.vision.KeyPointDetectionResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for the description of the structure.
|
||||
|
||||
### 类成员属性
|
||||
#### 后处理参数
|
||||
用户可按照自己的实际需求，修改下列后处理参数，从而影响最终的推理和部署效果
|
||||
### Class Member Property
|
||||
#### Post-processing Parameter
|
||||
Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
|
||||
|
||||
> > * **use_dark**(bool): 是否使用DARK进行后处理[参考论文](https://arxiv.org/abs/1910.06278)
|
||||
> > * **use_dark**(bool): • Whether to use DARK for post-processing. Refer to [Reference Paper](https://arxiv.org/abs/1910.06278)
|
||||
|
||||
|
||||
## 其它文档
|
||||
## Other Documents
|
||||
|
||||
- [PP-TinyPose 模型介绍](..)
|
||||
- [PP-TinyPose C++部署](../cpp)
|
||||
- [模型预测结果说明](../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
- [PP-TinyPose Model Description](..)
|
||||
- [PP-TinyPose C++ Deployment](../cpp)
|
||||
- [Model Prediction Results](../../../../../docs/api/vision_results/)
|
||||
- [How to switch the model inference backend engine](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
|
||||
@@ -0,0 +1,82 @@
|
||||
[English](README.md) | 简体中文
|
||||
# PP-TinyPose Python部署示例
|
||||
|
||||
在部署前，需确认以下两个步骤
|
||||
|
||||
- 1. 软硬件环境满足要求，参考[FastDeploy环境要求](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. 根据开发环境，下载预编译部署库和samples代码，参考[FastDeploy预编译库](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
|
||||
本目录下提供`pptinypose_infer.py`快速完成PP-TinyPose在CPU/GPU，以及GPU上通过TensorRT加速部署的`单图单人关键点检测`示例。执行如下脚本即可完成
|
||||
|
||||
>> **注意**: PP-Tinypose单模型目前只支持单图单人关键点检测，因此输入的图片应只包含一个人或者进行过裁剪的图像。多人关键点检测请参考[PP-TinyPose Pipeline](../../det_keypoint_unite/python/README.md)
|
||||
|
||||
```bash
|
||||
#下载部署示例代码
|
||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||
cd FastDeploy/examples/vision/keypointdetection/tiny_pose/python
|
||||
|
||||
# 下载PP-TinyPose模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_TinyPose_256x192_infer.tgz
|
||||
tar -xvf PP_TinyPose_256x192_infer.tgz
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/hrnet_demo.jpg
|
||||
|
||||
# CPU推理
|
||||
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device cpu
|
||||
# GPU推理
|
||||
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device gpu
|
||||
# GPU上使用TensorRT推理 （注意：TensorRT推理第一次运行，有序列化模型的操作，有一定耗时，需要耐心等待）
|
||||
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device gpu --use_trt True
|
||||
# 昆仑芯XPU推理
|
||||
python pptinypose_infer.py --tinypose_model_dir PP_TinyPose_256x192_infer --image hrnet_demo.jpg --device kunlunxin
|
||||
```
|
||||
|
||||
运行完成可视化结果如下图所示
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/16222477/196386764-dd51ad56-c410-4c54-9580-643f282f5a83.jpeg", width=359px, height=423px />
|
||||
</div>
|
||||
|
||||
## PP-TinyPose Python接口
|
||||
|
||||
```python
|
||||
fd.vision.keypointdetection.PPTinyPose(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
|
||||
```
|
||||
|
||||
PP-TinyPose模型加载和初始化，其中model_file, params_file以及config_file为训练模型导出的Paddle inference文件，具体请参考其文档说明[模型导出](https://github.com/PaddlePaddle/PaddleDetection/blob/release/2.5/deploy/EXPORT_MODEL.md)
|
||||
|
||||
**参数**
|
||||
|
||||
> * **model_file**(str): 模型文件路径
|
||||
> * **params_file**(str): 参数文件路径
|
||||
> * **config_file**(str): 推理部署配置文件
|
||||
> * **runtime_option**(RuntimeOption): 后端推理配置，默认为None，即采用默认配置
|
||||
> * **model_format**(ModelFormat): 模型格式，默认为Paddle格式
|
||||
|
||||
### predict函数
|
||||
|
||||
> ```python
|
||||
> PPTinyPose.predict(input_image)
|
||||
> ```
|
||||
>
|
||||
> 模型预测结口，输入图像直接输出检测结果。
|
||||
>
|
||||
> **参数**
|
||||
>
|
||||
> > * **input_image**(np.ndarray): 输入数据，注意需为HWC，BGR格式
|
||||
|
||||
> **返回**
|
||||
>
|
||||
> > 返回`fastdeploy.vision.KeyPointDetectionResult`结构体，结构体说明参考文档[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
|
||||
### 类成员属性
|
||||
#### 后处理参数
|
||||
用户可按照自己的实际需求，修改下列后处理参数，从而影响最终的推理和部署效果
|
||||
|
||||
> > * **use_dark**(bool): 是否使用DARK进行后处理[参考论文](https://arxiv.org/abs/1910.06278)
|
||||
|
||||
|
||||
## 其它文档
|
||||
|
||||
- [PP-TinyPose 模型介绍](..)
|
||||
- [PP-TinyPose C++部署](../cpp)
|
||||
- [模型预测结果说明](../../../../../docs/api/vision_results/)
|
||||
- [如何切换模型推理后端引擎](../../../../../docs/cn/faq/how_to_change_backend.md)
|
||||
Reference in New Issue
Block a user