why the Implement of Blstm is different to the paper describle?

oyxhust / CNN-LSTM-CTC-text-recognition

CNN and LSTM model for text recognition

259 stars 88 forks source link

why the Implement of Blstm is different to the paper describle? #10

Open novioleo opened 6 years ago

novioleo commented 6 years ago

I tried to train crnn with chinese scene text,i noticed that it's so slow than crnn in pytorch version~ i checked the code and i found the blstm is so different to the author's version,how do you think about it?