Skip to content

Latest commit

 

History

History
70 lines (52 loc) · 2.88 KB

README-orginal.md

File metadata and controls

70 lines (52 loc) · 2.88 KB
Raw

yolov5

The Pytorch implementation is ultralytics/yolov5.

Currently, we support yolov5 v1.0(yolov5s only), v2.0, v3.0 and v3.1.

Config

  • Choose the model s/m/l/x by NET macro in yolov5.cpp
  • Input shape defined in yololayer.h
  • Number of classes defined in yololayer.h, DO NOT FORGET TO ADAPT THIS, If using your own model
  • FP16/FP32 can be selected by the macro in yolov5.cpp
  • GPU id can be selected by the macro in yolov5.cpp
  • NMS thresh in yolov5.cpp
  • BBox confidence thresh in yolov5.cpp
  • Batch size in yolov5.cpp

How to Run, yolov5s as example

1. generate yolov5s.wts from pytorch with yolov5s.pt, or download .wts from model zoo

git clone https://github.com/wang-xinyu/tensorrtx.git
git clone https://github.com/ultralytics/yolov5.git
// download its weights 'yolov5s.pt'
// copy tensorrtx/yolov5/gen_wts.py into ultralytics/yolov5
// ensure the file name is yolov5s.pt and yolov5s.wts in gen_wts.py
// go to ultralytics/yolov5
python gen_wts.py
// a file 'yolov5s.wts' will be generated.

2. build tensorrtx/yolov5 and run

// put yolov5s.wts into tensorrtx/yolov5
// go to tensorrtx/yolov5
// ensure the macro NET in yolov5.cpp is s
// update CLASS_NUM in yololayer.h if your model is trained on custom dataset
mkdir build
cd build
cmake ..
make
sudo ./yolov5 -s             // serialize model to plan file i.e. 'yolov5s.engine'
sudo ./yolov5 -d  ../samples // deserialize plan file and run inference, the images in samples will be processed.

3. check the images generated, as follows. _zidane.jpg and _bus.jpg

4. optional, load and run the tensorrt model in python

// install python-tensorrt, pycuda, etc.
// ensure the yolov5s.engine and libmyplugins.so have been built
python yolov5_trt.py

More Information

See the readme in home page.