Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Migrate to TensorFlow r1.0 and Python 3 #7

Open
wants to merge 18 commits into
base: master
Choose a base branch
from
Open

Migrate to TensorFlow r1.0 and Python 3 #7

wants to merge 18 commits into from

Conversation

tindzk
Copy link

@tindzk tindzk commented Apr 2, 2017

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 simplifications.

tindzk added 18 commits March 25, 2017 23:14
@tindzk
Migrate to latest TensorFlow version and Python 3
fe1d162
@tindzk
utils: Simplify list_to_string()
a0fbffa
@tindzk
train_generator: Minor cleanup
1ab7b5c
@tindzk
generate: Fix compilation
fece810
@tindzk
model: Fix minor problems
cb591e9
@tindzk
Create logs for TensorBoard
b3745ce
@tindzk
model: Improve readability of decode_layer()
e3b9bed
@tindzk
model: Remove ReLU from decoder's final convolution
fd9fefd
@tindzk
ops: Use He uniform variance scaling in conv1d()
ff13a37
@tindzk
ops: Shorten final statement in conv1d()
fff09fc
@tindzk
train_generator: Improve logging
fb11494 
As in https://github.com/ibab/tensorflow-wavenet
@tindzk
ops: Use as_list() in time_to_batch() and batch_to_time()
c50cff4
@tindzk
ops: trainable is already set to True in get_variable()
5b7c7a5
@tindzk
ops: Merge padded assignments
9ebe688
@tindzk
ops: Extract shapes for better readability
bba0dc0
@tindzk
Update README
562243d
@tindzk
ops: Use truncated normal distribution in conv1d()
a76c102
@tindzk
model: Restore ReLU before final convolution in decoder
c95f424
@paarthneekhara
Copy link
Owner

Hi,
Thanks for that pull request! I had not been maintaining this repo. I'll go through it and merge. Did you evaluate the results for machine translation?

@tindzk
Copy link
Author

tindzk commented Apr 2, 2017

Thanks! In my refactoring I mostly focused on the prediction model. The training semantics has not changed.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers
No reviews
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@tindzk @paarthneekhara