geduo15 / very-deep-convolutional-networks-for-natural-language-processing-in-tensorflow Goto Github PK

I am sorry, I can not find the code. And only a file about accuracy found.

Hi there,

Thank you for showing your code.
Can you please tell us where we can get the dataset from?

Cheers

1. The trainable argument in the batch_norm op should be replaced with is_trainable.
2. I think the starting convolution layer is incorrect. In my opinion, this stride should be [1, 1, ,1, 1] instead of [1, 1, embedding_size, 1], and padding=Valid instead of padding=Same should be used.