mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
Update PaddleClas and PaddleSeg doc (#108)
* Update README.md * Update README.md * Update README.md * Create README.md * Update README.md * Update README.md * Update README.md * Update README.md * Add evaluation calculate time and fix some bugs * Update classification __init__ * Move to ppseg * Add segmentation doc * Add PaddleClas infer.py * Update PaddleClas infer.py * Delete .infer.py.swp * Add PaddleClas infer.cc * Update README.md * Update README.md * Update README.md * Update infer.py Co-authored-by: Jason <jiangjiajun@baidu.com>
This commit is contained in:
huangjianhui
@@ -1,62 +1,65 @@
|
||||
# YOLOv7 C++部署示例
|
||||
# PaddleClas C++部署示例
|
||||
|
||||
本目录下提供`infer.cc`快速完成YOLOv7在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
|
||||
本目录下提供`infer.cc`快速完成PaddleClas系列模型在CPU/GPU，以及GPU上通过TensorRT加速部署的示例。
|
||||
|
||||
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/quick_start/requirements.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/compile/prebuilt_libraries.md)
|
||||
|
||||
以Linux上CPU推理为例，在本目录执行如下命令即可完成编译测试
|
||||
以Linux上ResNet50_vd推理为例，在本目录执行如下命令即可完成编译测试
|
||||
|
||||
```
|
||||
#下载SDK，编译模型examples代码（SDK中包含了examples代码）
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/libs/0.2.0/fastdeploy-linux-x64-gpu-0.2.0.tgz
|
||||
tar xvf fastdeploy-linux-x64-gpu-0.2.0.tgz
|
||||
cd fastdeploy-linux-x64-gpu-0.2.0/examples/vision/classification/paddleclas/cpp
|
||||
mkdir build
|
||||
cd build
|
||||
wget https://xxx.tgz
|
||||
tar xvf fastdeploy-linux-x64-0.2.0.tgz
|
||||
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/fastdeploy-linux-x64-0.2.0
|
||||
cmake .. -DFASTDEPLOY_INSTALL_DIR=${PWD}/../../../../../../fastdeploy-linux-x64-gpu-0.2.0
|
||||
make -j
|
||||
|
||||
#下载官方转换好的yolov7模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/yolov7.onnx
|
||||
wget https://gitee.com/paddlepaddle/PaddleDetection/raw/release/2.4/demo/000000087038.jpg
|
||||
# 下载ResNet50_vd模型文件和测试图片
|
||||
wget https://bj.bcebos.com/paddlehub/fastdeploy/ResNet50_vd_infer.tgz
|
||||
tar -xvf ResNet50_vd_infer.tgz
|
||||
wget https://gitee.com/paddlepaddle/PaddleClas/raw/release/2.4/deploy/images/ImageNet/ILSVRC2012_val_00000010.jpeg
|
||||
|
||||
|
||||
# CPU推理
|
||||
./infer_demo yolov7.onnx 000000087038.jpg 0
|
||||
./infer_demo ResNet50_vd_infer ILSVRC2012_val_00000010.jpeg 0
|
||||
# GPU推理
|
||||
./infer_demo yolov7.onnx 000000087038.jpg 1
|
||||
./infer_demo ResNet50_vd_infer ILSVRC2012_val_00000010.jpeg 1
|
||||
# GPU上TensorRT推理
|
||||
./infer_demo yolov7.onnx 000000087038.jpg 2
|
||||
./infer_demo ResNet50_vd_infer ILSVRC2012_val_00000010.jpeg 2
|
||||
```
|
||||
|
||||
## YOLOv7 C++接口
|
||||
## PaddleClas C++接口
|
||||
|
||||
### YOLOv7类
|
||||
### PaddleClas类
|
||||
|
||||
```
|
||||
fastdeploy::vision::detection::YOLOv7(
|
||||
fastdeploy::vision::classification::PaddleClasModel(
|
||||
const string& model_file,
|
||||
const string& params_file = "",
|
||||
const string& params_file,
|
||||
const string& config_file,
|
||||
const RuntimeOption& runtime_option = RuntimeOption(),
|
||||
const Frontend& model_format = Frontend::ONNX)
|
||||
const Frontend& model_format = Frontend::PADDLE)
|
||||
```
|
||||
|
||||
YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式。
|
||||
PaddleClas模型加载和初始化，其中model_file, params_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/PaddleClas/blob/release/2.4/docs/zh_CN/inference_deployment/export_model.md#2-%E5%88%86%E7%B1%BB%E6%A8%A1%E5%9E%8B%E5%AF%BC%E5%87%BA)
|
||||
|
||||
**参数**
|
||||
|
||||
> * **model_file**(str): 模型文件路径
|
||||
> * **params_file**(str): 参数文件路径，当模型格式为ONNX时，此参数传入空字符串即可
|
||||
> * **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**(Frontend): 模型格式，默认为ONNX格式
|
||||
> * **model_format**(Frontend): 模型格式，默认为Paddle格式
|
||||
|
||||
#### Predict函数
|
||||
|
||||
> ```
|
||||
> YOLOv7::Predict(cv::Mat* im, DetectionResult* result,
|
||||
> float conf_threshold = 0.25,
|
||||
> float nms_iou_threshold = 0.5)
|
||||
> PaddleClasModel::Predict(cv::Mat* im, ClassifyResult* result, int topk = 1)
|
||||
> ```
|
||||
>
|
||||
> 模型预测接口，输入图像直接输出检测结果。
|
||||
@@ -64,13 +67,9 @@ YOLOv7模型加载和初始化，其中model_file为导出的ONNX模型格式。
|
||||
> **参数**
|
||||
>
|
||||
> > * **im**: 输入图像，注意需为HWC，BGR格式
|
||||
> > * **result**: 检测结果，包括检测框，各个框的置信度, DetectionResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
> > * **conf_threshold**: 检测框置信度过滤阈值
|
||||
> > * **nms_iou_threshold**: NMS处理过程中iou阈值
|
||||
> > * **result**: 分类结果，包括label_id，以及相应的置信度, ClassifyResult说明参考[视觉模型预测结果](../../../../../docs/api/vision_results/)
|
||||
> > * **topk**(int):返回预测概率最高的topk个分类结果，默认为1
|
||||
|
||||
### 类成员变量
|
||||
|
||||
> > * **size**(vector<int>): 通过此参数修改预处理过程中resize的大小，包含两个整型元素，表示[width, height], 默认值为[640, 640]
|
||||
|
||||
- [模型介绍](../../)
|
||||
- [Python部署](../python)
|
||||
|
||||
Reference in New Issue
Block a user