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

Wrong implementation of Generator #22

Closed
seungwonpark opened this issue Nov 4, 2019 · 3 comments
Closed

Wrong implementation of Generator #22

seungwonpark opened this issue Nov 4, 2019 · 3 comments
Assignees
@seungwonpark

Comments

@seungwonpark
Copy link
Owner

The last layer should be:

nn.utils.weight_norm(nn.Conv1d(32, 1, kernel_size=7, stride=1, padding=3)),

not:

nn.utils.weight_norm(nn.ConvTranspose1d(32, 1, kernel_size=7, stride=1, padding=3)),

omg...
@seungwonpark seungwonpark self-assigned this Nov 4, 2019
@seungwonpark
Copy link
Owner Author

Working on this at fix/22 branch.

I'll be training the model from scratch and upload audio samples again. I wonder why the previous model was working well.

@bob80333
Copy link

bob80333 commented Nov 5, 2019 •
edited
Loading

As far as why it worked so well, this article trains a CNN image classifier with Conv2d and ConvTranspose2d using the same hyperparameters for both and gets almost identical results.

@seungwonpark
Copy link
Owner Author

The new version looks working well. I will merge it to master branch after the pre-trained model is ready. Also, will update the audio samples.

seungwonpark added a commit that referenced this issue Nov 11, 2019
@seungwonpark
upload fixed samples (#22)
c26733f
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@seungwonpark seungwonpark

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@bob80333 @seungwonpark