apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-28 18:51:58 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Update docs

Browse Source
This commit is contained in:
felixhjh
2023-02-08 16:33:12 +00:00
parent bc3a7ce8fe
commit 844d80ecae
61 changed files with 1117 additions and 2519 deletions
Download Patch File Download Diff File Expand all files Collapse all files

88
examples/vision/segmentation/paddleseg/ascend/python/README.md Executable file → Normal file
View File

@@ -1,82 +1,36 @@
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
Before deployment, two steps require confirmation
本目录下提供`infer.py`快速完成PP-LiteSeg在华为昇腾上部署的示例。
- 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)
## 华为昇腾NPU编译FastDeploy wheel包环境准备
在部署前，需自行编译基于华为昇腾NPU的FastDeploy python wheel包并安装，参考文档[华为昇腾NPU部署环境编译](https://github.com/PaddlePaddle/FastDeploy/blob/develop/docs/cn/build_and_install#自行编译安装)
>>**注意** **PP-Matting**、**PP-HumanMatting**的模型，请从[Matting模型部署](../../../ppmatting)下载
【Attention】For the deployment of **PP-Matting**、**PP-HumanMatting** and **ModNet**, refer to [Matting Model Deployment](../../../matting)
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
git clone https://github.com/PaddlePaddle/FastDeploy.git
cd FastDeploy/examples/vision/segmentation/paddleseg/python
#下载部署示例代码
cd path/to/paddleseg/ascend/cpp
# 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PP-LiteSeg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
# 华为昇腾推理
python infer.py --model PP_LiteSeg_B_STDC2_cityscapes_without_argmax_infer --image cityscapes_demo.png
```
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)