暂无描述

sierkinhane bb7b87d260 delete log 5 年之前
.idea bb7b87d260 delete log 5 年之前
images 332a59abc7 beauty 5 年之前
lib bb7b87d260 delete log 5 年之前
output bb7b87d260 delete log 5 年之前
README.md 85d127d6b0 add labels processing 5 年之前
demo.py 8bd599cba4 update readme 5 年之前
train.py bb7b87d260 delete log 5 年之前

README.md

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 labels in here (password: w877)

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

    test.txt

    20456343_4045240981.jpg 89 201 241 178 19 94 19 22 26 656
    20457281_3395886438.jpg 120 1061 2 376 78 249 272 272 120 1061
    ...
    

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