Update GradientModifier to be an in-place operation #123
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
mzweilin
reviewed
Mar 31, 2023
| def __call__(self, grad: torch.Tensor) -> torch.Tensor: | ||
| return grad.sign() | ||
| def __call__(self, parameters: torch.Tensor | Iterable[torch.Tensor]) -> None: | ||
| if isinstance(parameters, torch.Tensor): |
Contributor
There was a problem hiding this comment.
We wouldn't need a batch-aware GradientModifier if we accept the shared modality-iterable-dispatch mechanism in #115
Member
Author
|
@mzweilin: I think it's better to merge this before the generic dispatch mechanism because it updates the tests. |
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Outdated suggestions cannot be applied.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.
What does this PR do?
This PR updates GradientModifier to be an in-place operation like torch.nn.utils.clip_grad_norm_. This also adds a test to make sure Adversary is properly modifying gradients.
Type of change
Please check all relevant options.
Testing
Please describe the tests that you ran to verify your changes. Consider listing any relevant details of your test configuration.
make testCIFAR10_CNN_Advachieves ~70% accuracyBefore submitting
pre-commit run -acommand without errorsDid you have fun?
Make sure you had fun coding 🙃