Add unpatch to dropconnect #198
Merged
Conversation
This file contains 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
parmidaatg
requested changes
Apr 5, 2022
| if not changed: | ||
| warnings.warn("No layer was modified by patch_module!", UserWarning) | ||
| return module | ||
|
|
||
|
|
||
| def _patch_layers(module: torch.nn.Module, layers: Sequence, weight_dropout: float) -> bool: | ||
| def unpatch_module(module: torch.nn.Module, inplace: bool = True) -> torch.nn.Module: |
There was a problem hiding this comment.
Is there a way that we can reduce the duplications for patch_module and unpatch_module ?
I understand that we don't want to expose the user to the unnecessary complexities hence not using the mapping_fn as an input so maybe there is not other way around
There was a problem hiding this comment.
you are right, we could uniformize all of these.
parmidaatg
approved these changes
Apr 5, 2022
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Summary:
This is a bit hacky as we need to keep the "old" Dropout value, but I think this does what it needs.
Features:
Checklist:
tests/documentation_test.py).