LPRNet_Pytorch

LPRNet_Pytorch

Pytorch Implementation For LPRNet, A High Performance And Lightweight License Plate Recognition Framework.
It is fully applicable to Chinese license plate recognition and foreign license plate recognition!
Currently, only Chinese license plates such as blue and green license plates are supported at the same time, which are new energy license plates, but other types of license plates can be supported by expanding training data or fine-tuning to improve the recognition accuracy!

Dependencies

• pytorch >= 1.0.0
• opencv-python 3.x
• python 3.x
• imutils
• Pillow
• numpy

pretrained model

• pretrained_model

training and testing

1. prepare your datasets, image size must be 94x24.
2. base on your datsets path modify the scripts its hyperparameters --train_img_dirs or --test_img_dirs.
3. adjust other hyperparameters if need.
4. run 'python train_LPRNet.py' or 'python test_LPRNet.py'.
5. if want to show testing result, add '--show true' or '--show 1' to run command.

performance

• personal test datasets.
• include blue/green license plate.
• images are very widely.
• total test images number is 27320.

size	personal test imgs(%)	inference@gtx 1060(ms)
1.7M	96.0+	0.5-

References

1. LPRNet: License Plate Recognition via Deep Neural Networks
2. PyTorch Chinese Documentation

postscript

If you found this useful, please give me a star, thanks!