Skip to content

ieee820/crnn_chinese_characters_rec

 
 

Repository files navigation

Crnn_chinese_characters_rec

chinese characters recognition

Test

There are images in test_images file, and you just run as follow.

python3 test.py

Train

before traning, you should prepare the dataset of characters.(described in csdn blog)

python3 crnn_main.py --train_root (path of train lmdb dataset) --val_root (path of val lmdb dataset) --cuda(if have)

3.6 million chinese characters dataset:

Results:

Training(accuray was 97.7% ultimately):

About

chinese characters recognition

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%