Open ghost opened 5 years ago
If you look at "Model.py", it seems to be helpful.
def ctc_lambda_func(args):
y_pred, labels, input_length, label_length = args
# the 2 is critical here since the first couple outputs of the RNN
# tend to be garbage:
y_pred = y_pred[:, 2:, :]
return K.ctc_batch_cost(labels, y_pred, input_length, label_length)
Hi, in the line
why you used
in the out varibale.