Fix BiasBatchNorm2d layer and Pyramid implementation #31
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
fabiansinz
requested changes
Mar 15, 2018
| super().__init__(features, **kwargs) | ||
| self.bias = nn.Parameter(torch.Tensor(features)) | ||
| super().__init__() | ||
| self.bn = nn.BatchNorm2d(features, **kwargs) |
Contributor
There was a problem hiding this comment.
Shouldn't that have an affine=False by default then?
Member
Author
There was a problem hiding this comment.
affine=False would allow the user to override it and also suggests that you can change the behavior. Given this, I prefer to simply fix the value in the init
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
BiasBatchNorm2dno longer works. I have updated the implementation to be cleaner and hopefully less dependent on the exact implementation ofnn.BatchNorm2dandnn.ModulePyramidimplementation is now fixed to follow the standard Laplace image pyramid implementation. Some special parameters are added to maintain backward compatibility with the already trained networks usingPyramid.