History

Huang ZhuangZhuang 2e53f0cae7 update infer preprocessing (#623 ) There are some problems with the preprocessing on LPRnet when infer, which will cause the predicted output results to be inconsistent with the pytorch version; as shown, the preprocessing has been updated here		2021-07-15 12:46:18 +08:00
..
1.jpg	add LPRNet (#430 )	2021-03-04 17:29:19 +08:00
CMakeLists.txt	add LPRNet (#430 )	2021-03-04 17:29:19 +08:00
genwts.py	add LPRNet (#430 )	2021-03-04 17:29:19 +08:00
logging.h	add LPRNet (#430 )	2021-03-04 17:29:19 +08:00
LPRnet.cpp	update infer preprocessing (#623 )	2021-07-15 12:46:18 +08:00
README.md	update readme	2021-03-05 15:10:42 +08:00

README.md

LPRNet

The Pytorch implementation is xuexingyu24/License_Plate_Detection_Pytorch.

How to Run

generate LPRnet.wts from pytorch

git clone https://github.com/wang-xinyu/tensorrtx.git
git clone https://github.com/xuexingyu24/License_Plate_Detection_Pytorch.git

// copy tensorrtx/LRPnet/gen_wts.py to License_Plate_Detection_Pytorch/
// go to License_Plate_Detection_Pytorch/
python genwts.py
// a file 'LPRnet.wts' will be generated.

build LPRnet and run

// put LPRnet.wts into tensorrtx/LPRnet
// go to tensorrtx/LPRnet
mkdir build
cd build
cmake ..
make
sudo ./LPRnet -s  // serialize model to file i.e. 'LPRnet.engine'
sudo ./LPRnet -d  // deserialize model and run inference