CRNN_Chinese_Characters_Rec

Characters Recognition

A Chinese characters recognition repository based on convolutional recurrent networks.

Performance

Recognize characters in pictures

Dev Environments

1. WIN 10 or Ubuntu 16.04
2. PyTorch 1.4.0 (may fix ctc loss)
3. yaml
4. easydict

Data

Synthetic Chinese String Dataset

1. Download the dataset in here

2. Edit lib/config/360CC_config.yaml DATA:ROOT to you image path

   DATASET:
     ROOT: 'to/your/images/path'
   

3. Put char_std_5990.txt in lib/dataset/txt/

4. Download the preprocessed labels in here (password: w877)

5. And put train.txt and test.txt in lib/dataset/txt/

Train

   [run] python train.py --cfg lib/config/360CC_config.yaml

loss curve

   [run] cd output/360CC/crnn/xxxx-xx-xx-xx-xx/
   [run] tensorboard --log_dir log

loss overview

Demo

   [run] python demo.py --image_path images/test.png --checkpoints output/checkpoints/mixed_second_finetune_acc_97P7.pth

References

• https://github.com/meijieru/crnn.pytorch
• https://github.com/HRNet