Paarth Neekhara

Just an update in case you are still following this. I rewrote almost the complete model. I noticed there was a bug in the encoder for the translation model earlier...

For filter_width=3, dilation=1 => dilation/2 = 0 => (filter_width - 1) * dilation/2 = 0 . So the input will not be padded.

The padding setting for the decoder is correct. ``` padding = [[0, 0], [(filter_width - 1) * dilation, 0], [0, 0]] ``` This is done to preserve the causality. Refer...

Oh, I see. I just went through the documentation of tf.nn.conv1d. It seems that the input may be paded differently for different input lengths, which is not desirable. Changing it...

@zcyang Updated the ops. The model works correctly now. It was indeed an error in encoder padding. Check ```Model/ops``` for the new implementation.