Refine code structure (#89)

* refine code structure

* refine code structure
This commit is contained in:
Jason
2022-08-10 10:50:22 +08:00
committed by GitHub
parent c7d37b6732
commit 22ca63982b
333 changed files with 1 additions and 37500 deletions

View File

@@ -0,0 +1,77 @@
# YOLOv7 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。
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/prebuild_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
```
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
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
# CPU推理
./infer_demo yolov7.onnx 000000087038.jpg 0
# GPU推理
./infer_demo yolov7.onnx 000000087038.jpg 1
# GPU上TensorRT推理
./infer_demo yolov7.onnx 000000087038.jpg 2
```
## YOLOv7 C++接口
### YOLOv7类
```
fastdeploy::vision::detection::YOLOv7(
const string& model_file,
const string& params_file = "",
const RuntimeOption& runtime_option = RuntimeOption(),
const Frontend& model_format = Frontend::ONNX)
```
YOLOv7模型加载和初始化其中model_file为导出的ONNX模型格式。
**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
> * **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
#### Predict函数
> ```
> YOLOv7::Predict(cv::Mat* im, DetectionResult* result,
> float conf_threshold = 0.25,
> float nms_iou_threshold = 0.5)
> ```
>
> 模型预测接口,输入图像直接输出检测结果。
>
> **参数**
>
> > * **im**: 输入图像注意需为HWCBGR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
### 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)
- [视觉模型预测结果](../../../../../docs/api/vision_results/)