Skip to content

Convolutional Recurrent Neural Network (CRNN) Implement with pytorch for chinese OCR

Notifications You must be signed in to change notification settings

dcrmg/CRNN_OCR_pytorch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Convolutional Recurrent Neural Network (CRNN) Implement with pytorch for chinese OCR.

  1. Prepare training data, you can find samples(with labels) in the folder of "data", it looks like:

Alt text

Alt text

  1. Create LMDB database cd create_dataset python create_dataset.py

  2. train CRNN for chinese OCR cd pytorch-train python crnn_main.py --cuda

you can find trained model in the folder of "save_model"

notes:

  1. needs to be carefully confirmed whether your Chinese characters are in alphabet or not.
  2. good performance in training accuracy, and bad performance in practical application? maybe samples of various situations are needed.

About

Convolutional Recurrent Neural Network (CRNN) Implement with pytorch for chinese OCR

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages