Skip to content

seyosum/detector-tensorrt-yolov5-linux

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

this repo tensorrt's version is TensorRT-7.0.0.11.Ubuntu-16.04.x86_64-gnu.cuda-10.2.cudnn7.6.tar.gz

requirements

  • cuda 10.2+
  • cudnn 7.6+
  • opencv

how to build

1.add model.pt file to model dir
2.use tools/gen_wts.py generate model.wts file
3.use loadWeightsToEngineFile(model.wts,engine_name) generate model.engine file(the example is in main.cpp) or you can call loadWeightsToEngineFile by python,java,etc.
4.please call init() method once before doing anything
5.the test/test.py is a example that how python call .so

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • C++ 71.4%
  • Python 20.8%
  • C 5.9%
  • Cuda 1.6%
  • CMake 0.1%
  • Dockerfile 0.1%
  • Shell 0.1%