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

5971-fix the pixelshuffle upsample shape mismatch problem. #5982

Merged
merged 3 commits into from
Feb 13, 2023

Conversation

binliunls
Copy link
Contributor

Signed-off-by: binliu binliu@nvidia.com

Fixes #5971 .

Description

There is a mismatch shape between the conv weight and input shape in FlexibleUNet, if using pixelshuffle upsampling method. This is caused by the wrong initialized pre_conv parameter in the decoder, which should be default instead of None. Fixed this question in this PR by changing it to default and adding some test cases.

Types of changes

  • Non-breaking change (fix or new feature that would not break existing functionality).
  • Breaking change (fix or new feature that would cause existing functionality to change).
  • New tests added to cover the changes.
  • Integration tests passed locally by running ./runtests.sh -f -u --net --coverage.
  • Quick tests passed locally by running ./runtests.sh --quick --unittests --disttests.
  • In-line docstrings updated.
  • Documentation updated, tested make html command in the docs/ folder.

Signed-off-by: binliu <binliu@nvidia.com>
@Nic-Ma
Copy link
Contributor

Nic-Ma commented Feb 13, 2023

@wyli
Copy link
Contributor

wyli commented Feb 13, 2023

/black

@wyli wyli force-pushed the 5971-fix-pixelshuffle-upsample branch from 9762097 to 6f404a9 Compare February 13, 2023 08:41
…e-upsample

Signed-off-by: Wenqi Li <wenqil@nvidia.com>
Signed-off-by: Wenqi Li <wenqil@nvidia.com>
@wyli
Copy link
Contributor

wyli commented Feb 13, 2023

/build

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.

Getting the wrong shape in training when pixelshuffle in FlexibleUNet
3 participants