byteNet-tensorflow

byteNet-tensorflow copied to clipboard

Hi, is it possible to share with us some of your pre-trained models? Thanks.

dreamibor

We can upgrade the code to compatible with tf1.0.0 by the following diff:

2

git diff diff --git a/ByteNet/model.py b/ByteNet/model.py index 4cfe3b3..3a12b5b 100644 --- a/ByteNet/model.py +++ b/ByteNet/model.py @@ -138,7 +138,7 @@ class Byte_net_model: decoder_output = self.decoder(source_embedding) loss = self.loss(decoder_output, target_sentence) - tf.scalar_summary('LOSS', loss) +...

SeekPoint

the padding for dilated convolution seems to be wrong

7

For encoder, the dilated convolution for encoder pads ``` (filter_width - 1) * dilation/2```, this means after reshaping there are ```(filter_width-1)``` zeros at the beginning. But ```conv1d``` uses ```SAME``` padding,...

zcyang

Consistency with the original paper?

9

Could you reproduce the result of language modeling in the original paper?

amirj

Migrate to TensorFlow r1.0 and Python 3

2

This pull request eliminates the warnings with the latest TensorFlow version. I have also refactored some functions for better readability. The code now requires Python 3, which lead to further...

tindzk

Translating

1

Hey awesome implementation. Thanks. In translate.py, when I want to translate a source sentence, I still need to provide a target. Is the target the same as the source? Thanks

talolard