oyxhust / CNN-LSTM-CTC-text-recognition

CNN and LSTM model for text recognition
259 stars 88 forks source link

why num_label is fixed? #5

Open fengxinjie opened 7 years ago

fengxinjie commented 7 years ago

Hi. In your code the num_label is fixed, and you pad zeros for short ones. Is it necessary? if not, Does it affect the speed of training?

oyxhust commented 7 years ago

It won't affect the speed of training. I set the max length for the "num_label", because this can reduce the error of output. When the length of prediction is longer than the max length, it is obviously wrong.

novioleo commented 6 years ago

@oyxhust so,you mean you just want to converge faster?