mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-06 00:57:33 +08:00
Update docs
This commit is contained in:
felixhjh
95
examples/vision/segmentation/paddleseg/cpu-gpu/python/README.md
Executable file → Normal file
95
examples/vision/segmentation/paddleseg/cpu-gpu/python/README.md
Executable file → Normal file
@@ -1,82 +1,45 @@
|
||||
English | [简体中文](README_CN.md)
|
||||
# PaddleSeg Python Deployment Example
|
||||
[English](README.md) | 简体中文
|
||||
# PaddleSeg Python部署示例
|
||||
本目录下提供`infer.py`快速完成PP-LiteSeg在CPU/GPU，以及GPU上通过Paddle-TensorRT加速部署的示例。执行如下脚本即可完成
|
||||
|
||||
Before deployment, two steps require confirmation
|
||||
## 部署环境准备
|
||||
|
||||
- 1. Software and hardware should meet the requirements. Please refer to [FastDeploy Environment Requirements](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. Install FastDeploy Python whl package. Refer to [FastDeploy Python Installation](../../../../../docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
在部署前，需确认软硬件环境，同时下载预编译python wheel 包，参考文档[FastDeploy预编译库安装](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install#FastDeploy预编译库安装)
|
||||
|
||||
【Attention】For the deployment of **PP-Matting**、**PP-HumanMatting** and **ModNet**, refer to [Matting Model Deployment](../../../matting)
|
||||
【注意】如你部署的为**PP-Matting**、**PP-HumanMatting**以及**ModNet**请参考[Matting模型部署](../../../ppmatting)
|
||||
|
||||
This directory provides examples that `infer.py` fast finishes the deployment of Unet on CPU/GPU and GPU accelerated by TensorRT. The script is as follows
|
||||
```bash
|
||||
# Download the deployment example code
|
||||
#下载部署示例代码
|
||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||
cd FastDeploy/examples/vision/segmentation/paddleseg/python
|
||||
cd FastDeploy/examples/vision/segmentation/paddleseg/cpu-gpu/python
|
||||
|
||||
# Download Unet model files and test images
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/Unet_cityscapes_without_argmax_infer.tgz
|
||||
tar -xvf Unet_cityscapes_without_argmax_infer.tgz
|
||||
# 下载Unet模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer.tgz
|
||||
tar -xvf PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer.tgz
|
||||
wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png
|
||||
|
||||
# CPU inference
|
||||
python infer.py --model Unet_cityscapes_without_argmax_infer --image cityscapes_demo.png --device cpu
|
||||
# GPU inference
|
||||
python infer.py --model Unet_cityscapes_without_argmax_infer --image cityscapes_demo.png --device gpu
|
||||
# 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 infer.py --model Unet_cityscapes_without_argmax_infer --image cityscapes_demo.png --device gpu --use_trt True
|
||||
# kunlunxin XPU inference
|
||||
python infer.py --model Unet_cityscapes_without_argmax_infer --image cityscapes_demo.png --device kunlunxin
|
||||
# CPU推理
|
||||
python infer.py --model PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer --image cityscapes_demo.png --device cpu
|
||||
# GPU推理
|
||||
python infer.py --model PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer --image cityscapes_demo.png --device gpu
|
||||
# GPU上使用Paddle-TensorRT推理 （注意：Paddle-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 infer.py --model PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer --image cityscapes_demo.png --device gpu --use_trt True
|
||||
```
|
||||
|
||||
The visualized result after running is as follows
|
||||
运行完成可视化结果如下图所示
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/16222477/191712880-91ae128d-247a-43e0-b1e3-cafae78431e0.jpg", width=512px, height=256px />
|
||||
</div>
|
||||
|
||||
## PaddleSegModel Python Interface
|
||||
## 快速链接
|
||||
- [PaddleSeg python API文档](https://www.paddlepaddle.org.cn/fastdeploy-api-doc/python/html/semantic_segmentation.html)
|
||||
- [FastDeploy部署PaddleSeg模型概览](..)
|
||||
- [PaddleSeg C++部署](../cpp)
|
||||
|
||||
```python
|
||||
fd.vision.segmentation.PaddleSegModel(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
|
||||
```
|
||||
|
||||
PaddleSeg 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/PaddleSeg/blob/develop/docs/model_export_cn.md) for more information
|
||||
|
||||
**Parameter**
|
||||
|
||||
> * **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 function
|
||||
|
||||
> ```python
|
||||
> PaddleSegModel.predict(input_image)
|
||||
> ```
|
||||
>
|
||||
> Model prediction interface. Input images and output detection results.
|
||||
>
|
||||
> **Parameter**
|
||||
>
|
||||
> > * **input_image**(np.ndarray): Input data in HWC or BGR format
|
||||
|
||||
> **Return**
|
||||
>
|
||||
> > Return `fastdeploy.vision.SegmentationResult` structure. Refer to [Vision Model Prediction Results](../../../../../docs/api/vision_results/) for the description of the structure.
|
||||
|
||||
### Class Member Variable
|
||||
#### Pre-processing Parameter
|
||||
Users can modify the following pre-processing parameters to their needs, which affects the final inference and deployment results
|
||||
|
||||
> > * **is_vertical_screen**(bool): For PP-HumanSeg models, the input image is portrait with height greater than width by setting this parameter to `true`
|
||||
#### Post-processing Parameter
|
||||
> > * **apply_softmax**(bool): The `apply_softmax` parameter is not specified when the model is exported. Set this parameter to `true` to normalize the probability result (score_map) of the predicted output segmentation label (label_map) in softmax
|
||||
|
||||
## Other Documents
|
||||
|
||||
- [PaddleSeg Model Description](..)
|
||||
- [PaddleSeg 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)
|
||||
## 常见问题
|
||||
- [如何将模型预测结果SegmentationResult转为numpy格式](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/faq/vision_result_related_problems.md)
|
||||
- [如何切换模型推理后端引擎](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/faq/how_to_change_backend.md)
|
||||
- [Intel GPU(独立显卡/集成显卡)的使用](https://github.com/PaddlePaddle/FastDeploy/blob/develop/tutorials/intel_gpu/README.md)
|
||||
- [编译CPU部署库](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/cpu.md)
|
||||
- [编译GPU部署库](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/gpu.md)
|
||||
- [编译Jetson部署库](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/jetson.md)
|
||||
|
||||
@@ -1,88 +0,0 @@
|
||||
[English](README.md) | 简体中文
|
||||
# PaddleSeg 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](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
- 2. FastDeploy Python whl包安装，参考[FastDeploy Python安装](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/download_prebuilt_libraries.md)
|
||||
|
||||
【注意】如你部署的为**PP-Matting**、**PP-HumanMatting**以及**ModNet**请参考[Matting模型部署](../../../matting)
|
||||
|
||||
本目录下提供`infer.py`快速完成PP-LiteSeg在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。执行如下脚本即可完成
|
||||
|
||||
```bash
|
||||
#下载部署示例代码
|
||||
git clone https://github.com/PaddlePaddle/FastDeploy.git
|
||||
cd FastDeploy/examples/vision/segmentation/paddleseg/cpu-gpu/python
|
||||
|
||||
# 下载Unet模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer.tgz
|
||||
tar -xvf PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer.tgz
|
||||
wget https://paddleseg.bj.bcebos.com/dygraph/demo/cityscapes_demo.png
|
||||
|
||||
# CPU推理
|
||||
python infer.py --model PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer --image cityscapes_demo.png --device cpu
|
||||
# GPU推理
|
||||
python infer.py --model PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer --image cityscapes_demo.png --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 infer.py --model PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer --image cityscapes_demo.png --device gpu --use_trt True
|
||||
```
|
||||
|
||||
运行完成可视化结果如下图所示
|
||||
<div align="center">
|
||||
<img src="https://user-images.githubusercontent.com/16222477/191712880-91ae128d-247a-43e0-b1e3-cafae78431e0.jpg", width=512px, height=256px />
|
||||
</div>
|
||||
|
||||
## PaddleSegModel Python接口
|
||||
|
||||
```python
|
||||
fd.vision.segmentation.PaddleSegModel(model_file, params_file, config_file, runtime_option=None, model_format=ModelFormat.PADDLE)
|
||||
```
|
||||
|
||||
PaddleSeg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/PaddleSeg/blob/develop/docs/model_export_cn.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
|
||||
> PaddleSegModel.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.SegmentationResult`结构体，结构体说明参考文档[SegmentationResult结构体介绍](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/api/vision_results/segmentation_result_CN.md)
|
||||
|
||||
### 类成员属性
|
||||
#### 预处理参数
|
||||
用户可按照自己的实际需求，修改下列预处理参数，从而影响最终的推理和部署效果
|
||||
|
||||
> > * **is_vertical_screen**(bool): PP-HumanSeg系列模型通过设置此参数为`true`表明输入图片是竖屏，即height大于width的图片
|
||||
|
||||
#### 后处理参数
|
||||
> > * **apply_softmax**(bool): 当模型导出时，并未指定`apply_softmax`参数，可通过此设置此参数为`true`，将预测的输出分割标签（label_map）对应的概率结果(score_map)做softmax归一化处理
|
||||
|
||||
## 其它文档
|
||||
|
||||
- [PaddleSeg 模型介绍](..)
|
||||
- [PaddleSeg C++部署](../cpp)
|
||||
|
||||
## 常见问题
|
||||
- [如何将模型预测结果SegmentationResult转为numpy格式](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/api/vision_results/segmentation_result_CN.md)
|
||||
- [如何切换模型推理后端引擎](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/faq/how_to_change_backend.md)
|
||||
- [Intel GPU(独立显卡/集成显卡)的使用](https://github.com/PaddlePaddle/FastDeploy/blob/develop/tutorials/intel_gpu/README.md)
|
||||
- [PaddleSeg python API文档](https://www.paddlepaddle.org.cn/fastdeploy-api-doc/python/html/semantic_segmentation.html)
|
||||
- [编译CPU部署库](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/cpu.md)
|
||||
- [编译GPU部署库](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install/gpu.md)
|
||||
@@ -32,6 +32,10 @@ def build_option(args):
|
||||
|
||||
if args.use_trt:
|
||||
option.use_trt_backend()
|
||||
# If use original Tensorrt, not Paddle-TensorRT,
|
||||
# comment the following two lines
|
||||
option.enable_paddle_to_trt()
|
||||
option.enable_paddle_trt_collect_shape()
|
||||
option.set_trt_input_shape("x", [1, 3, 256, 256], [1, 3, 1024, 1024],
|
||||
[1, 3, 2048, 2048])
|
||||
return option
|
||||
|
||||
Reference in New Issue
Block a user