GRCNN.pytorch

Introduction

This is a pytorch implementation of Gated Recurrent Convolution Neural Network for OCR.
A CRNN implementation is in https://github.com/jingjing-you/CRNN_OCR.pytorch.

Requirements

1. Pytorch >= 0.4.0
   
2. opencv
   
3. warp_ctc_pytorch
4. tqdm

Construct dataset

The names of train and val data are constructed as bellow:

img_xxx_$$$.jpg

where 'xxx' represents the number of this image and '$$$' represents the label of this image. For example，‘img_0_WHLU.jpg’.

Other examples are in data_sample/ directory.

Training the model

You can run python train.py to train your model.

Evaluation

You can run python eval.py to test your model.

References

1. https://github.com/meijieru/crnn.pytorch
   
2. https://github.com/Jianfeng1991/GRCNN-for-OCR