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.

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

Fix bug in LSTM cell in synthesizer/models/modules.py #374

Merged
1 commit merged into from Jun 24, 2020
Merged

Fix bug in LSTM cell in synthesizer/models/modules.py #374

1 commit merged into from Jun 24, 2020

Conversation

ghost
Copy link

@ghost ghost commented Jun 24, 2020

This fixes a bug that was introduced in #366. In code to optimize CPU/GPU performance of the synthesizer, the GPU call is missing an argument. This resolves #337 and #344 .

Another option is to pass the num_layers argument to tf.contrib.cudnn_rnn.CudnnLSTM, but it is deprecated. Reverting seems like the better option here.

@ghost
Copy link
Author

ghost commented Jun 24, 2020

Here is a link to the affected line of code along with my comments:
1b8d2e7#r40127321

@ghost ghost requested a review from CorentinJ June 24, 2020 06:19
@ghost ghost merged commit 3f8f891 into CorentinJ:master Jun 24, 2020
@ghost ghost deleted the 373_cudnn_lstm_arg_error branch June 24, 2020 11:33
This pull request was closed.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

TypeError on line 114 of \synthesizer\models\odules.py (pusalieth fork)
1 participant