[Feature] Add Zero-shot Knowledge Transfer via Adversarial Belief Matching #241
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
Codecov Report
@@ Coverage Diff @@
## dev-1.x #241 +/- ##
==========================================
- Coverage 0.44% 0.44% -0.01%
==========================================
Files 161 163 +2
Lines 6506 6545 +39
Branches 1064 1068 +4
==========================================
Hits 29 29
- Misses 6472 6511 +39
Partials 5 5
Flags with carried forward coverage won't be shown. Click here to find out more.
Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here. |
fpshuang
reviewed
Aug 23, 2022
| volume={32}, | ||
| year={2019} | ||
| } | ||
| ``` |
There was a problem hiding this comment.
add Acknowledgement: appreciate Davidgzx's contribution
fpshuang
reviewed
Aug 23, 2022
|
|
||
| def forward(self, | ||
| data: Optional[torch.Tensor] = None, | ||
| batch_size: int = 0) -> torch.Tensor: |
There was a problem hiding this comment.
batch_size defaulted to 0?
fpshuang
reviewed
Aug 23, 2022
sunnyxiaohu
reviewed
Aug 24, 2022
mmrazor/models/losses/at_loss.py
Outdated
| loss = (self.at(s_feature) - self.at(t_feature)).pow(2).mean() | ||
| return self.loss_weight * loss | ||
|
|
||
| def at(self, x: torch.Tensor) -> torch.Tensor: |
There was a problem hiding this comment.
make the method name meaningfull and clear, such as at -> calc_attention_matrix
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Outdated suggestions cannot be applied.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.
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers.
Motivation
Add a data-free distillation algorithm named Zero-shot Knowledge Transfer via Adversarial Belief Matching.
Modification
1.Add generaor (zskt_generator) and loss (at_loss) for zskt.
2.Add config, readme, image for zskt.
BC-breaking (Optional)
Does the modification introduce changes that break the backward compatibility of the downstream repositories?
If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR.
Use cases (Optional)
If this PR introduces a new feature, it is better to list some use cases here and update the documentation.
Checklist
Before PR:
After PR: