search

Holmeyoung / crnn-pytorch

Pytorch implementation of CRNN (CNN + RNN + CTCLoss) for all language OCR.
MIT License
378 stars 105 forks source link

Batchnormalization layer #55

Closed Zrufy closed 4 years ago

Zrufy commented 4 years ago

I tried to do a training without the normalization layers.I noticed that the training is stalled and the value during the training always returns the same letter.The normalization layer is therefore necessary? Or simply the network takes more time for the training?