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

Add CFA model (#783) #28

Merged
merged 1 commit into from
Jan 12, 2023
Merged

Conversation

NagatoYuki0943
Copy link
Owner

  • Initial cfa commit

  • Initial cfa commit

  • Initial cfa commit

  • Revert Padim changes'

  • Rename variables

  • rename model to feature extractor

  • Added the old implementation

  • Initial commit for the second roun nd

  • Renamed DSVDD to CfaModel

  • Set optimizer with model.parameters()

  • Create get_feature_extractor function

  • Rename model to feature-extractor in CfaModel

  • Add compute_loss to forward

  • Remove saved images

  • Create anomaly heatmap generator for cfa model

  • Rename Descriptor variables and backbone names

  • Replace feature extractor with torchfx. Works for wide-resnet

  • Feature extractor inside CFA model now works!

  • Removed trainer-cfa2

  • Create cfa tests

  • Feature extractor inside the CFA model returns the same output

  • Added docstring

  • Worked on anomaly map generation

  • All the tests are passing now

  • Step 0: Setup the new refactoring pipeline.

  • Step 1 Replace descriptor with our descriptor

  • Step 2: Refactor init_centroid

  • Step 2: Refactor forward, loss and anomaly-map

  • Step 3: Replaced feature extractor with the new one.

  • Step 4: Replace dataloader with anomalib dataloader.

  • Step 5: Add the lightnign module

  • Step 6: Add the new CLI config file

  • Step 7: Remove the scripts belonging to the old implementation

  • Step 8: Added readme file

  • Set max-epochs to 30

  • Address pre-commit issues

  • Add tests

  • Fix blur tests

  • Fix load weight tests

  • Added benchmark results

  • Update the main readme file

  • Remove AUPRO from the config file

  • Added cfa results to docs

  • Add anomaly map generator class

  • Update anomalib/models/cfa/config.yaml

Co-authored-by: Dick Ameln [email protected]

  • Add the original license of coord2d

  • Add F1 Scores to the config file

  • Revert "Add F1 Scores to the config file"

This reverts commit 7752bb3.

  • Modified config file to adapt to the new format

  • dryrun_find_featuremap_dims functiion to get the feature dimensions of the backbones.

  • Address pylint and mypy issues

  • Update the changelog

Co-authored-by: Dick Ameln [email protected]

Description

  • Provide a summary of the modification as well as the issue that has been resolved. List any dependencies that this modification necessitates.

  • Fixes # (issue)

Changes

  • Bug fix (non-breaking change which fixes an issue)
  • Refactor (non-breaking change which refactors the code base)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to not work as expected)
  • This change requires a documentation update

Checklist

  • My code follows the pre-commit style and check guidelines of this project.
  • I have performed a self-review of my code
  • I have commented my code, particularly in hard-to-understand areas
  • I have made corresponding changes to the documentation
  • My changes generate no new warnings
  • I have added tests that prove my fix is effective or that my feature works
  • New and existing tests pass locally with my changes
  • I have added a summary of my changes to the CHANGELOG (not for minor changes, docs and tests).

* Initial cfa commit

* Initial cfa commit

* Initial cfa commit

* Revert Padim changes'

* Rename variables

* rename model to feature extractor

* Added the old implementation

* Initial commit for the second roun nd

* Renamed DSVDD to CfaModel

* Set optimizer with model.parameters()

* Create get_feature_extractor function

* Rename model to feature-extractor in CfaModel

* Add compute_loss to forward

* Remove saved images

* Create anomaly heatmap generator for cfa model

* Rename Descriptor variables and backbone names

* Replace feature extractor with torchfx. Works for wide-resnet

* Feature extractor inside CFA model now works!

* Removed trainer-cfa2

* Create cfa tests

* Feature extractor inside the CFA model returns the same output

* Added docstring

* Worked on anomaly map generation

* All the tests are passing now

* Step 0: Setup the new refactoring pipeline.

* Step 1 Replace descriptor with our descriptor

* Step 2: Refactor init_centroid

* Step 2: Refactor forward, loss and anomaly-map

* Step 3: Replaced feature extractor with the new one.

* Step 4: Replace dataloader with anomalib dataloader.

* Step 5: Add the lightnign module

* Step 6: Add the new CLI config file

* Step 7: Remove the scripts belonging to the old implementation

* Step 8: Added readme file

* Set max-epochs to 30

* Address pre-commit issues

* Add tests

* Fix blur tests

* Fix load weight tests

* Added benchmark results

* Update the main readme file

* Remove AUPRO from the config file

* Added cfa results to docs

* Add anomaly map generator class

* Update anomalib/models/cfa/config.yaml

Co-authored-by: Dick Ameln <[email protected]>

* Add the original license of coord2d

* Add F1 Scores to the config file

* Revert "Add F1 Scores to the config file"

This reverts commit 7752bb3.

* Modified config file to adapt to the new format

* dryrun_find_featuremap_dims functiion to get the feature dimensions of the backbones.

* Address pylint and mypy issues

* Update the changelog

Co-authored-by: Dick Ameln <[email protected]>
@NagatoYuki0943 NagatoYuki0943 merged commit a9afd81 into NagatoYuki0943:main Jan 12, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants