-
Notifications
You must be signed in to change notification settings - Fork 459
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
Feat/conv transpose2d #574
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
See comment.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I agree with @louisfd if we can use the existing initializer then we should it it.
I also had a comment about group divisibility.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Looks good. Thanks for fixing the issues.
你好,我有一个请求,就是能够实现一下上采样吗?(Upsample),类似https://pytorch.org/docs/stable/generated/torch.nn.Upsample.html |
@Zheby
Please file a separate ticket. There is a related ticket: #455 |
Related Issues/PRs
Partial Fix #540 (ConvTranspose1D to be done in a following PR)
Changes
Change the init method for all convolution modules to be similar to PyTorch.
Conv1D: https://pytorch.org/docs/stable/generated/torch.nn.Conv1d.html
Conv2D: https://pytorch.org/docs/stable/generated/torch.nn.Conv2d.html
ConvTranspose2D: https://pytorch.org/docs/stable/generated/torch.nn.ConvTranspose2d.html
Fix init methods, shapes and documentation when using
groups > 1