History

BaofengZan a65be9152a Revert "hrnet classification trt 加速" This reverts commit 9e1c282158087e6d18217559ab66d1393ec3ad17.		2020-11-06 23:20:31 +08:00
..
CMakeLists.txt	hrnet clasification trt 加速	2020-11-06 23:19:23 +08:00
demo.py	hrnet clasification trt 加速	2020-11-06 23:19:23 +08:00
hrnet.cpp	Revert "hrnet classification trt 加速"	2020-11-06 23:20:31 +08:00
logging.h	hrnet clasification trt 加速	2020-11-06 23:19:23 +08:00
readme.md	hrnet classification trt 加速	2020-11-06 23:19:23 +08:00

readme.md

HRNet

The Pytorch implementation is HRNet-Image-Classification.

How to Run

1. generate .wts
Download code and model from HRNet-Image-Classification and config your environments.

Put demo.py in the YOUR_ROOT_DIR\HRNet-Image-Classification\tools folder, set savewts in main() as True, and run, the .wts will be generated.

cmake and make

mkdir build
cd build
cmake ..
make
sudo ./dbnet -s             // serialize model to plan file i.e. 'DBNet.engine'
sudo ./dbnet -d  ../samples // deserialize plan file and run inference, the images in samples will be processed.

Result

The test img:

Pytorch Result:

TRT Result: