we0091234/yolov7-face-tensorrt 开源项目中文解读：技术栈、适用场景与上手建议

项目介绍

we0091234/yolov7-face-tensorrt 是一个托管在 GitHub 上的开源项目，主要使用 C++ 编写，目前获得 47 个 Star、8 次 Fork。

仓库全名: we0091234/yolov7-face-tensorrt

README 摘要

yolov7-face TensorRT yolov7-face The Pytorch implementation is yolov7-face. onnx export step1. git clone https://github.com/derronqi/yolov7-face step2. modify models/export.py step3. modify models/yolo.py class IKeypoint step4. Export to onnx model How to Run, yolov7s-face as example 1. Modify the tensorrt cuda opencv path in CMakeLists.txt 2. build 3. onnx to tensorrt model 4. inference The results are saved in the…

完整内容见 GitHub 原始 README 或本页。

常见问题

yolov7-face-tensorrt 用什么语言开发？

主要使用 C++ 编写，目前有 47 个 Star。

如何获取 yolov7-face-tensorrt 的源码？

可以直接克隆仓库：git clone https://github.com/we0091234/yolov7-face-tensorrt.git，默认分支为 master；安装与运行步骤见仓库 README。

yolov7-face-tensorrt 最近还在维护吗？

仓库最近一次更新为 2023年2月24日，当前有 8 个未关闭 Issue；Star 数为 47，可作为社区活跃度的参考。

关于

yolov7-face tensorrt

face-detection face-landmark-detection yolov5-face yolov5-face-landmark yolov7 yolov7-face

47 Stars
8 Forks
1 Watching

描述取自 GitHub 官方 API，中文内容由 GitRead 中文社区编辑团队整理。

简要分析

热度分

价值分

活跃状态

活跃

GitHub

语言占比

C++

CMake

Cuda

贡献者

we0091234

yolov7-face TensorRT

yolov7-face

The Pytorch implementation is yolov7-face.

onnx export

step1. git clone https://github.com/derronqi/yolov7-face

step2. modify models/export.py

 #line 72
 #output_names = None
 # modified into:
 output_names = ["output"]

step3. modify models/yolo.py class IKeypoint

#line 308
# return x if self.training else (torch.cat(z, 1), x)
# modified into:
return x if self.training else torch.cat(z, 1)

step4. Export to onnx model

 cd yolov7-face
 python models/export.py --weights yolov7s-face.pt --grid

How to Run, yolov7s-face as example

Modify the tensorrt cuda opencv path in CMakeLists.txt

#cuda 
include_directories(/mnt/Gu/softWare/cuda-11.0/targets/x86_64-linux/include)
link_directories(/mnt/Gu/softWare/cuda-11.0/targets/x86_64-linux/lib)

#tensorrt 
include_directories(/mnt/Gpan/tensorRT/TensorRT-8.2.0.6/include/)
link_directories(/mnt/Gpan/tensorRT/TensorRT-8.2.0.6/lib/)

build

1. mkdir build
2. cd build
3. cmake ..
4. make

onnx to tensorrt model

./onnx2trt/onnx2trt  ../onnx_model/yolov7s-face.onnx ./yolov7s-face.trt  1

inference
```
./yolov7_face yolov7s-face.trt ../images
```
The results are saved in the build folder.

contact

Tencent qq group: 871797331

暂无评论

yolov7-face-tensorrt