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

mutual infomration algoritm for DG #878

Merged
merged 20 commits into from
Oct 15, 2024
Merged

mutual infomration algoritm for DG #878

merged 20 commits into from
Oct 15, 2024

Conversation

smilesun
Copy link
Collaborator

No description provided.

@codecov-commenter
Copy link

codecov-commenter commented Sep 19, 2024

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 95.35%. Comparing base (8ea9aa2) to head (7ab5e0a).
Report is 22 commits behind head on master.

Additional details and impacted files
@@            Coverage Diff             @@
##           master     #878      +/-   ##
==========================================
+ Coverage   95.25%   95.35%   +0.10%     
==========================================
  Files         133      137       +4     
  Lines        5291     5409     +118     
==========================================
+ Hits         5040     5158     +118     
  Misses        251      251              
Flag Coverage Δ
unittests 95.35% <100.00%> (+0.10%) ⬆️

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

@smilesun smilesun changed the title tempalte miro, why encoder is constant? mutual infomration algoritm for DG Oct 5, 2024
@smilesun smilesun assigned smilesun and unassigned agisga Oct 5, 2024



class URResNet(torch.nn.Module):
Copy link
Collaborator Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

use a wraper to let each layer of arbitrary nn to keep the features during the training , alternatively, only keep the last layer, two versions use inheritance

Copy link
Collaborator Author

@smilesun smilesun left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

wrapper for torch module to keep feature at each layer

@smilesun smilesun merged commit 8dafe68 into master Oct 15, 2024
1 of 2 checks passed
@smilesun smilesun deleted the miro branch October 15, 2024 14:26
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.

3 participants