Skip to content

🚀 feat(post-processing): Add MEBin post processor from AnomalyNCD #3089

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.

Sign up for GitHub

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

Jump to bottom
Closed
StarPlatinum7 wants to merge 44 commits into from
Closed

🚀 feat(post-processing): Add MEBin post processor from AnomalyNCD #3089

StarPlatinum7 wants to merge 44 commits into from

Conversation

@StarPlatinum7
Copy link

@StarPlatinum7 StarPlatinum7 commented Nov 6, 2025

📝 Description

✨ Changes

Select what type of change your PR is:

  • 🚀 New feature (non-breaking change which adds functionality)
  • 🐞 Bug fix (non-breaking change which fixes an issue)
  • 🔄 Refactor (non-breaking change which refactors the code base)
  • ⚡ Performance improvements
  • 🎨 Style changes (code style/formatting)
  • 🧪 Tests (adding/modifying tests)
  • 📚 Documentation update
  • 📦 Build system changes
  • 🚧 CI/CD configuration
  • 🔧 Chore (general maintenance)
  • 🔒 Security update
  • 💥 Breaking change (fix or feature that would cause existing functionality to not work as expected)

✅ Checklist

Before you submit your pull request, please make sure you have completed the following steps:

  • 📚 I have made the necessary updates to the documentation (if applicable).
  • 🧪 I have written tests that support my changes and prove that my fix is effective or my feature works (if applicable).
  • 🏷️ My PR title follows conventional commit format.

For more information about code review checklists, see the Code Review Checklist.

alfieroddan and others added 30 commits November 6, 2025 19:32
@alfieroddan @StarPlatinum7
🐛 fix(model): Reduce memory reserved for memory bank based models Pat…
b243ec5 
…chCore, Padim, Dfkde (#2913)

* refactor patchcore, use list instead of cat

* typo in patchcore

Signed-off-by: Alfie Roddan <[email protected]>

* padim model to now use cat instead of list

Signed-off-by: Alfie Roddan <[email protected]>

* dfm and padim update cat to list

Signed-off-by: Alfie Roddan <[email protected]>

* add dfkde cat to list changes

Signed-off-by: Alfie Roddan <[email protected]>

* change assert from memory bank to list size, fix pre-commit issues

Signed-off-by: Alfie Roddan <[email protected]>

---------

Signed-off-by: Alfie Roddan <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@StarPlatinum7
add mebin postprocessor
86bd8ba 
Signed-off-by: StarPlatinum7 <[email protected]>
@StarPlatinum7
test mebin postprocessor
58d2bd3 
Signed-off-by: StarPlatinum7 <[email protected]>
@StarPlatinum7
test mebin postprocessor
0818555 
Signed-off-by: StarPlatinum7 <[email protected]>
@abc-125 @samet-akcay @StarPlatinum7
🚀 feat(metric): added histogram of anomaly scores (#2920)
e7b838d 
* added histogram of anomaly scores

* Update src/anomalib/metrics/anomaly_score_distribution.py

Co-authored-by: Samet Akcay <[email protected]>
Signed-off-by: Aimira Baitieva <[email protected]>

* Update anomaly_score_distribution.py

* Update anomaly_score_distribution.py

* Fixed pre-commit checks

---------

Signed-off-by: Aimira Baitieva <[email protected]>
Co-authored-by: Samet Akcay <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@abc-125 @samet-akcay
@rajeshgangireddy @StarPlatinum7
🚀 feat(metric): added PGn, PBn metrics (#2889)
13d12ef 
* added pg and pb metrics

* fixed typos

* Update __init__.py

* Update __init__.py - removed duplicate

* Update pg_pb.py

* Fixed pre-commit checks

---------

Co-authored-by: Samet Akcay <[email protected]>
Co-authored-by: Rajesh Gangireddy <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(huggingface): Fix Bandit security issue B615 - HF Models (#2937)
8053ecb 
* 🐛 fix(huggingface): specify 'main' revision for model and processor loading.
Fixes Bandit security issue B615 (unsafe download without revision pinning)

* 🐛 fix(huggingface): add model_revision parameter for reproducible model loading

* 🐛 fix(model): add hf_model_revision parameter for specifying HuggingFace model revisions

* 🐛 fix(vlm_ad): set default values for api_key and hf_model_revision in _setup_vlm_backend method

* 🐛 fix(vlm_ad): rename huggingface_model_revision parameter to hf_model_revision for consistency

* 🐛 fix(vlm_ad): update model initialization parameters for consistency

* Update src/anomalib/models/image/vlm_ad/lightning_model.py

Co-authored-by: Copilot <[email protected]>
Signed-off-by: Rajesh Gangireddy <[email protected]>

* 🐛 fix(vlm_ad): change ALLOWED_HF_MODELS to frozenset for immutability

* 🐛 fix(vlm_ad): use ALLOWED_HF_MODELS for model validation in hf_model_revision

Signed-off-by: rajeshgangireddy <[email protected]>

---------

Signed-off-by: Rajesh Gangireddy <[email protected]>
Signed-off-by: rajeshgangireddy <[email protected]>
Co-authored-by: Copilot <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@oep-renovate @StarPlatinum7
chore(deps): update github actions (#2921)
8defc3d 
Signed-off-by: oep-renovate[bot] <212772560+oep-renovate[bot]@users.noreply.github.com>
Co-authored-by: oep-renovate[bot] <212772560+oep-renovate[bot]@users.noreply.github.com>
Signed-off-by: StarPlatinum7 <[email protected]>
@abc-125 @StarPlatinum7
🚀 feat(data): added ground truth masks to VAD dataset (#2940)
aad56a2 
added ground truth masks to VAD dataset

Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(bandit): Suppress Bandit NoSec incorrectly flagging HuggingFace…
6a85430 
… model loading (#2947)

Signed-off-by: Rajesh Gangireddy <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(docs): Update documentation and log messages to reflect recent …
1a21389 
…changes (#2931)

🐛 fix(docs): Update installation messages for missing dependencies in various modules

Signed-off-by: StarPlatinum7 <[email protected]>
@kamillipka @StarPlatinum7
🚀 feat(workflow): add CodeQL analysis workflow for security scanning (#…
17b0be5 
…2951)

* 🚀 feat(workflow): add CodeQL analysis workflow for security scanning

Signed-off-by: Lipka, Kamil <[email protected]>

* fix(workflow): remove whitespaces

Signed-off-by: Lipka, Kamil <[email protected]>

* format codeql.yml with prettier

Signed-off-by: Lipka, Kamil <[email protected]>

* refactor(workflow): update CodeQL workflow for clarity and efficiency

Signed-off-by: Lipka, Kamil <[email protected]>

* fix(workflow): correct action name for CodeQL analysis step

Signed-off-by: Lipka, Kamil <[email protected]>

* fix(workflow): remove unnecessary whitespace in CodeQL job permissions

Signed-off-by: Lipka, Kamil <[email protected]>

---------

Signed-off-by: Lipka, Kamil <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@samet-akcay @StarPlatinum7
🚀 feat(data): add backward compatibility methods and update docstring…
fb44a31 
… examples (#2950)

* fix(data): enable pin_memory for DataLoader instances across the codebase

This commit updates various DataLoader instances in the project to enable the  option, enhancing performance for data loading on GPU. Changes were made in the following files:

- : Updated train and test DataLoader configurations.
- : Modified datamodule DataLoader to include .
- : Added  to evaluation DataLoader.
- : Updated DataLoader for datasets to utilize .
- : Enabled  for reference dataset DataLoader.
- : Adjusted inference DataLoader to include .

These changes aim to optimize memory usage and improve data transfer speeds during model training and inference.

Signed-off-by: samet-akcay <[email protected]>

* refactor(models): streamline decoder retrieval in  function

This commit refactors the  function in  to utilize a dictionary mapping for decoder architectures, improving readability and maintainability. The previous conditional checks have been replaced with a more efficient approach, enhancing the overall structure of the code.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update logit_scale initialization to use torch.log for consistency

This commit modifies the initialization of the logit_scale parameter in the CLIP model to utilize torch.log instead of np.log. This change ensures consistency in tensor operations and improves compatibility with PyTorch's computation graph.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update anomaly map generation to use torch tensors for calculations

This commit modifies the anomaly map generation logic to utilize PyTorch tensors instead of NumPy arrays for various calculations. This change enhances compatibility with the PyTorch computation graph and improves performance by leveraging GPU acceleration. Key updates include the conversion of statistical calculations and tensor operations to use PyTorch functions, ensuring consistency in tensor handling throughout the code.

Signed-off-by: samet-akcay <[email protected]>

* refactor(model): enhance anomaly map generation with PyTorch for statistical calculations

This commit refactors the anomaly map generation logic to replace NumPy-based statistical calculations with PyTorch equivalents, specifically using the  distribution for computing tau. Additionally, it improves precision handling by allowing the use of float64 in high precision mode. The changes streamline the computation process and maintain compatibility with the PyTorch computation graph.

Signed-off-by: samet-akcay <[email protected]>

* chore(license): update license year

Signed-off-by: samet-akcay <[email protected]>

* fix(download): enhance URL validation and update download logic

This commit improves the URL validation in the download function to ensure only http and https schemes are allowed. Additionally, it adds comments to clarify the safety of using  under these conditions, enhancing code readability and security awareness.

Signed-off-by: samet-akcay <[email protected]>

* 🔧 chore: update copyright year and add keys method to NumpyBatch and Batch classes

This commit updates the copyright year in the Numpy and Torch base files to reflect 2024-2025. Additionally, it introduces a new `keys` method in both the `NumpyBatch` and `Batch` classes, allowing users to retrieve field names with an option to include or exclude fields with None values. The `__getitem__` method is also added to enable dictionary-like access to field values.

Signed-off-by: [Your Name] <[Your Email]>

* fix mypy

Signed-off-by: samet-akcay <[email protected]>

* refactor: improve dataset name and category handling in ImageVisualizer

This commit updates the ImageVisualizer class to handle dataset name and category attributes more robustly by using None as the default value instead of empty strings. This change enhances clarity and ensures that the filename generation logic remains consistent when these attributes are not present.

Signed-off-by: Samet Akcay [email protected]

* refactor: unify visualization method naming in ImageVisualizer

This commit refactors the ImageVisualizer class by renaming the `visualize_image` method to `visualize`, streamlining the interface for users. The updated method signature and examples in the docstring reflect this change, ensuring consistency in how predictions are visualized. Additionally, the copyright year has been updated to 2024-2025.

Signed-off-by: Samet Akcay <[email protected]>

---------

Signed-off-by: samet-akcay <[email protected]>
Signed-off-by: [Your Name] <[Your Email]>
Signed-off-by: Samet Akcay [email protected]
Signed-off-by: Samet Akcay <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@samet-akcay @StarPlatinum7
🔄 refactor(utils): improve optional import handling across loggers an…
a526581 
…d model backends (#2954)

* fix(data): enable pin_memory for DataLoader instances across the codebase

This commit updates various DataLoader instances in the project to enable the  option, enhancing performance for data loading on GPU. Changes were made in the following files:

- : Updated train and test DataLoader configurations.
- : Modified datamodule DataLoader to include .
- : Added  to evaluation DataLoader.
- : Updated DataLoader for datasets to utilize .
- : Enabled  for reference dataset DataLoader.
- : Adjusted inference DataLoader to include .

These changes aim to optimize memory usage and improve data transfer speeds during model training and inference.

Signed-off-by: samet-akcay <[email protected]>

* refactor(models): streamline decoder retrieval in  function

This commit refactors the  function in  to utilize a dictionary mapping for decoder architectures, improving readability and maintainability. The previous conditional checks have been replaced with a more efficient approach, enhancing the overall structure of the code.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update logit_scale initialization to use torch.log for consistency

This commit modifies the initialization of the logit_scale parameter in the CLIP model to utilize torch.log instead of np.log. This change ensures consistency in tensor operations and improves compatibility with PyTorch's computation graph.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update anomaly map generation to use torch tensors for calculations

This commit modifies the anomaly map generation logic to utilize PyTorch tensors instead of NumPy arrays for various calculations. This change enhances compatibility with the PyTorch computation graph and improves performance by leveraging GPU acceleration. Key updates include the conversion of statistical calculations and tensor operations to use PyTorch functions, ensuring consistency in tensor handling throughout the code.

Signed-off-by: samet-akcay <[email protected]>

* refactor(model): enhance anomaly map generation with PyTorch for statistical calculations

This commit refactors the anomaly map generation logic to replace NumPy-based statistical calculations with PyTorch equivalents, specifically using the  distribution for computing tau. Additionally, it improves precision handling by allowing the use of float64 in high precision mode. The changes streamline the computation process and maintain compatibility with the PyTorch computation graph.

Signed-off-by: samet-akcay <[email protected]>

* chore(license): update license year

Signed-off-by: samet-akcay <[email protected]>

* fix(download): enhance URL validation and update download logic

This commit improves the URL validation in the download function to ensure only http and https schemes are allowed. Additionally, it adds comments to clarify the safety of using  under these conditions, enhancing code readability and security awareness.

Signed-off-by: samet-akcay <[email protected]>

* 🐛 fix(graph): Corrected isinstance check for logger types in GraphLogger class

* 🐛 fix(comet): Improve CometLogger import handling and provide a dummy class for missing dependency

* 🐛 fix(mlflow): Add dummy MLFlowLogger class for missing MLFlow dependency and improve import handling

* 🐛 fix(tensorboard): Improve TensorBoardLogger import handling and add dummy class for missing dependency

* 🐛 fix(wandb): Enhance WandbLogger import handling and add dummy class for missing dependency

* 🐛 fix(chat_gpt): Enhance dotenv import handling and update API key retrieval logic to account for missing dependency

* 🐛 fix(ollama): Improve import handling for Ollama dependency and add dummy class for missing package

* 🐛 fix(winclip): Improve import handling for open_clip dependency and raise informative error messages for missing package

* 🐛 fix(imports): Introduce OptionalImport class for cleaner handling of optional dependencies and update video and ollama modules to utilize it for improved error messaging.

* 🐛 fix(imports): Update error messaging in OptionalImport class to enhance clarity when dependencies are missing.

---------

Signed-off-by: samet-akcay <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(path): Remove filter to remove hidden files (#2955)
33d366d 
🐛 fix(path): remove filter to remove hidden files and add a warning log for the same

Signed-off-by: StarPlatinum7 <[email protected]>
@samet-akcay @StarPlatinum7
🐞 fix(utils): revert OptionalImport class to handle missing optiona…
f09bffd 
…l dependencies (#2956)

* fix(data): enable pin_memory for DataLoader instances across the codebase

This commit updates various DataLoader instances in the project to enable the  option, enhancing performance for data loading on GPU. Changes were made in the following files:

- : Updated train and test DataLoader configurations.
- : Modified datamodule DataLoader to include .
- : Added  to evaluation DataLoader.
- : Updated DataLoader for datasets to utilize .
- : Enabled  for reference dataset DataLoader.
- : Adjusted inference DataLoader to include .

These changes aim to optimize memory usage and improve data transfer speeds during model training and inference.

Signed-off-by: samet-akcay <[email protected]>

* refactor(models): streamline decoder retrieval in  function

This commit refactors the  function in  to utilize a dictionary mapping for decoder architectures, improving readability and maintainability. The previous conditional checks have been replaced with a more efficient approach, enhancing the overall structure of the code.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update logit_scale initialization to use torch.log for consistency

This commit modifies the initialization of the logit_scale parameter in the CLIP model to utilize torch.log instead of np.log. This change ensures consistency in tensor operations and improves compatibility with PyTorch's computation graph.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update anomaly map generation to use torch tensors for calculations

This commit modifies the anomaly map generation logic to utilize PyTorch tensors instead of NumPy arrays for various calculations. This change enhances compatibility with the PyTorch computation graph and improves performance by leveraging GPU acceleration. Key updates include the conversion of statistical calculations and tensor operations to use PyTorch functions, ensuring consistency in tensor handling throughout the code.

Signed-off-by: samet-akcay <[email protected]>

* refactor(model): enhance anomaly map generation with PyTorch for statistical calculations

This commit refactors the anomaly map generation logic to replace NumPy-based statistical calculations with PyTorch equivalents, specifically using the  distribution for computing tau. Additionally, it improves precision handling by allowing the use of float64 in high precision mode. The changes streamline the computation process and maintain compatibility with the PyTorch computation graph.

Signed-off-by: samet-akcay <[email protected]>

* chore(license): update license year

Signed-off-by: samet-akcay <[email protected]>

* fix(download): enhance URL validation and update download logic

This commit improves the URL validation in the download function to ensure only http and https schemes are allowed. Additionally, it adds comments to clarify the safety of using  under these conditions, enhancing code readability and security awareness.

Signed-off-by: samet-akcay <[email protected]>

* 🗑️ chore(imports): remove OptionalImport class for optional dependency handling

Signed-off-by: samet-akcay <[email protected]>

* 🐛 fix(imports): Replace OptionalImport with dummy classes for missing dependencies

This commit removes the OptionalImport class and introduces dummy classes for various loggers and video utilities when their respective dependencies are not installed. The changes enhance error messaging by providing clear instructions for installation, improving user experience when encountering missing packages.

Affected files:
- video.py
- comet.py
- mlflow.py
- tensorboard.py
- wandb.py
- ollama.py

Signed-off-by: samet-akcay <[email protected]>

---------

Signed-off-by: samet-akcay <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@ashwinvaidya17 @StarPlatinum7
🔨 fix(semgrep): ignore uv.lock in semgrep (#2972)
9ca3a0a 
ignore uv.lock in semgrep

Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@monzelr @StarPlatinum7
🐞 fix(utils): Run CS Flow model in eval() so the weights of the model…
2a12bd4 
… itself will not be modified (#2966)

fix in dryrun_find_featuremap_dims: run the model in eval() so the weights of the model itself will not be modified

Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(ovinferencer): Fix openvino cache directory (#2979)
4327146 
🐛 fix(ovinferencer): update cache folder name to 'openvino_cache' and ensure string path for set_property

Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(pr.yaml): Increase unit test timeout from 15 to 30 seconds (#2988)
08d9f43 
* 🐛 fix(pr.yaml): Increase unit test timeout from 15 to 30 seconds

* 🐛 fix(_reusable-test-suite.yaml): Update example timeout from 15 to 30 minutes

Signed-off-by: StarPlatinum7 <[email protected]>
@ashwinvaidya17 @StarPlatinum7
🐞 fix(data): Perlin noise generator masks (#2936)
af4cd2e 
* Fix synthetic masks + incorrect F1 score

Signed-off-by: Ashwin Vaidya <[email protected]>

* Renormalize instead of retry

Signed-off-by: Ashwin Vaidya <[email protected]>

* Fix imports

Signed-off-by: Ashwin Vaidya <[email protected]>

* Add rescaling around threshold

Signed-off-by: Ashwin Vaidya <[email protected]>

---------

Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@ashwinvaidya17 @StarPlatinum7
🚧 ci(tests): Use uv commands (#2999)
15a0df5 
* Use uv commands

Signed-off-by: Ashwin Vaidya <[email protected]>

* Add source activate step

Signed-off-by: Ashwin Vaidya <[email protected]>

---------

Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🚀 feat(model): Make coreset selection for patchcore faster (#2968)
f9862fa 
* 🚀 feat(model): make improvements for patchcore on xpu

* 🔄 refactor(k_center_greedy): remove profiling code.

Signed-off-by: rajeshgangireddy <[email protected]>

* 🚀 feat(benchmark): add seed setting for reproducibility in run_benchmark function

* 🔄 refactor(k_center_greedy): enhance device handling and remove unused benchmark scripts

* 🔄 refactor(k_center_greedy): remove the unused case of multiple centers  to simplify

* 🐞 fix(comments): update variable names

---------

Signed-off-by: rajeshgangireddy <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@oep-renovate @StarPlatinum7
chore(deps): update github actions (#2983)
6ec7397 
Signed-off-by: oep-renovate[bot] <212772560+oep-renovate[bot]@users.noreply.github.com>
Co-authored-by: oep-renovate[bot] <212772560+oep-renovate[bot]@users.noreply.github.com>
Signed-off-by: StarPlatinum7 <[email protected]>
@ashwinvaidya17 @code-dev05
@rajeshgangireddy @StarPlatinum7
🚀 feat(data): BMAD dataset (#3000)
a94545c 
* 🚀 feat(dataset): add BMAD dataset to Anomalib (#2900)

* Adding BMAD dataset to Anomalib

Signed-off-by: Devansh Agarwal <[email protected]>

* Fixed pre-commit hook errors

Signed-off-by: Devansh Agarwal <[email protected]>

---------

Signed-off-by: Devansh Agarwal <[email protected]>

* 🔧 refactor(data): Polish BMAD dataset (#2981)

* 🧹 Polish dataset

🧪 Add tests
📋 Fix documentation
🛠️  Minor fixes

Signed-off-by: Ashwin Vaidya <[email protected]>

* Update src/anomalib/data/datamodules/image/bmad.py

Co-authored-by: Rajesh Gangireddy <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>

---------

Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>
Co-authored-by: Rajesh Gangireddy <[email protected]>

* Fix mask_samples

Signed-off-by: Ashwin Vaidya <[email protected]>

---------

Signed-off-by: Devansh Agarwal <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>
Co-authored-by: Devansh Agarwal <[email protected]>
Co-authored-by: Rajesh Gangireddy <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@ashwinvaidya17 @PaulMcHard
@samet-akcay @monzelr @rajeshgangireddy @StarPlatinum7
🚀 feat(dataset): add 3D-ADAM dataset to Anomalib (#3003)
4b7574b 
* 🚀 feat(dataset): add 3D-ADAM dataset to Anomalib (#2986)

* 🐞 fix(utils): revert `OptionalImport` class to handle missing optional dependencies (#2956)

* fix(data): enable pin_memory for DataLoader instances across the codebase

This commit updates various DataLoader instances in the project to enable the  option, enhancing performance for data loading on GPU. Changes were made in the following files:

- : Updated train and test DataLoader configurations.
- : Modified datamodule DataLoader to include .
- : Added  to evaluation DataLoader.
- : Updated DataLoader for datasets to utilize .
- : Enabled  for reference dataset DataLoader.
- : Adjusted inference DataLoader to include .

These changes aim to optimize memory usage and improve data transfer speeds during model training and inference.

Signed-off-by: samet-akcay <[email protected]>

* refactor(models): streamline decoder retrieval in  function

This commit refactors the  function in  to utilize a dictionary mapping for decoder architectures, improving readability and maintainability. The previous conditional checks have been replaced with a more efficient approach, enhancing the overall structure of the code.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update logit_scale initialization to use torch.log for consistency

This commit modifies the initialization of the logit_scale parameter in the CLIP model to utilize torch.log instead of np.log. This change ensures consistency in tensor operations and improves compatibility with PyTorch's computation graph.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update anomaly map generation to use torch tensors for calculations

This commit modifies the anomaly map generation logic to utilize PyTorch tensors instead of NumPy arrays for various calculations. This change enhances compatibility with the PyTorch computation graph and improves performance by leveraging GPU acceleration. Key updates include the conversion of statistical calculations and tensor operations to use PyTorch functions, ensuring consistency in tensor handling throughout the code.

Signed-off-by: samet-akcay <[email protected]>

* refactor(model): enhance anomaly map generation with PyTorch for statistical calculations

This commit refactors the anomaly map generation logic to replace NumPy-based statistical calculations with PyTorch equivalents, specifically using the  distribution for computing tau. Additionally, it improves precision handling by allowing the use of float64 in high precision mode. The changes streamline the computation process and maintain compatibility with the PyTorch computation graph.

Signed-off-by: samet-akcay <[email protected]>

* chore(license): update license year

Signed-off-by: samet-akcay <[email protected]>

* fix(download): enhance URL validation and update download logic

This commit improves the URL validation in the download function to ensure only http and https schemes are allowed. Additionally, it adds comments to clarify the safety of using  under these conditions, enhancing code readability and security awareness.

Signed-off-by: samet-akcay <[email protected]>

* 🗑️ chore(imports): remove OptionalImport class for optional dependency handling

Signed-off-by: samet-akcay <[email protected]>

* 🐛 fix(imports): Replace OptionalImport with dummy classes for missing dependencies

This commit removes the OptionalImport class and introduces dummy classes for various loggers and video utilities when their respective dependencies are not installed. The changes enhance error messaging by providing clear instructions for installation, improving user experience when encountering missing packages.

Affected files:
- video.py
- comet.py
- mlflow.py
- tensorboard.py
- wandb.py
- ollama.py

Signed-off-by: samet-akcay <[email protected]>

---------

Signed-off-by: samet-akcay <[email protected]>
Signed-off-by: Paul McHard <[email protected]>

* Added 3D-ADAM Dataset

Signed-off-by: Paul McHard <[email protected]>

* Added tests and example config

Signed-off-by: Paul McHard <[email protected]>

* 🔨 fix(semgrep): ignore uv.lock in semgrep (#2972)

ignore uv.lock in semgrep

Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: Paul McHard <[email protected]>

* 🐞 fix(utils): Run CS Flow model in eval() so the weights of the model itself will not be modified (#2966)

fix in dryrun_find_featuremap_dims: run the model in eval() so the weights of the model itself will not be modified

Signed-off-by: Paul McHard <[email protected]>

* 🐛 fix(ovinferencer): Fix openvino cache directory  (#2979)

🐛 fix(ovinferencer): update cache folder name to 'openvino_cache' and ensure string path for set_property

Signed-off-by: Paul McHard <[email protected]>

* changes per PR and pre-commit checks

Signed-off-by: Paul McHard <[email protected]>

* resolve circular import issue

Signed-off-by: Paul McHard <[email protected]>

* Resolve DownloadInfo URL issue.

Signed-off-by: Paul McHard <[email protected]>

* Resolve DownloadInfo URL

Signed-off-by: Paul McHard <[email protected]>

* restore doc images ignored in error

Signed-off-by: Paul McHard <[email protected]>

* Removed prettier cache included in error, re-run pre-commit hooks

Signed-off-by: Paul McHard <[email protected]>

* explictly resolve EOF error on docs/source/examples

Signed-off-by: Paul McHard <[email protected]>

* resolve filename issue in adam3d test.

Signed-off-by: Paul McHard <[email protected]>

* Restore uv.lock

Signed-off-by: Paul McHard <[email protected]>

---------

Signed-off-by: samet-akcay <[email protected]>
Signed-off-by: Paul McHard <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: Paul McHard <[email protected]>
Co-authored-by: Samet Akcay <[email protected]>
Co-authored-by: Ashwin Vaidya <[email protected]>
Co-authored-by: Rune <[email protected]>
Co-authored-by: Rajesh Gangireddy <[email protected]>

* revert changes to example

Signed-off-by: Ashwin Vaidya <[email protected]>

* revert file permissions

Signed-off-by: Ashwin Vaidya <[email protected]>

* 🔧 refactor(data): Polish 3dAdam dataset  (#3002)

* Add changelog + fix dataset location

Signed-off-by: Ashwin Vaidya <[email protected]>

* revert changes to example

Signed-off-by: Ashwin Vaidya <[email protected]>

* revert file permissions

Signed-off-by: Ashwin Vaidya <[email protected]>

* Fix tests

Signed-off-by: Ashwin Vaidya <[email protected]>

---------

Signed-off-by: Ashwin Vaidya <[email protected]>

* revert examples

Signed-off-by: Ashwin Vaidya <[email protected]>

* revert file permissions

Signed-off-by: Ashwin Vaidya <[email protected]>

* Add imagecodecs dependency

Signed-off-by: Ashwin Vaidya <[email protected]>

* Apply suggestion from @samet-akcay

Co-authored-by: Samet Akcay <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>

---------

Signed-off-by: samet-akcay <[email protected]>
Signed-off-by: Paul McHard <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: Paul McHard <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>
Co-authored-by: Paul McHard <[email protected]>
Co-authored-by: Samet Akcay <[email protected]>
Co-authored-by: Rune <[email protected]>
Co-authored-by: Rajesh Gangireddy <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@samet-akcay @ashwinvaidya17
@StarPlatinum7
🔧 chore(release): prepare v2.2.0 release (#2960)
1edc95b 
* fix(data): enable pin_memory for DataLoader instances across the codebase

This commit updates various DataLoader instances in the project to enable the  option, enhancing performance for data loading on GPU. Changes were made in the following files:

- : Updated train and test DataLoader configurations.
- : Modified datamodule DataLoader to include .
- : Added  to evaluation DataLoader.
- : Updated DataLoader for datasets to utilize .
- : Enabled  for reference dataset DataLoader.
- : Adjusted inference DataLoader to include .

These changes aim to optimize memory usage and improve data transfer speeds during model training and inference.

Signed-off-by: samet-akcay <[email protected]>

* refactor(models): streamline decoder retrieval in  function

This commit refactors the  function in  to utilize a dictionary mapping for decoder architectures, improving readability and maintainability. The previous conditional checks have been replaced with a more efficient approach, enhancing the overall structure of the code.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update logit_scale initialization to use torch.log for consistency

This commit modifies the initialization of the logit_scale parameter in the CLIP model to utilize torch.log instead of np.log. This change ensures consistency in tensor operations and improves compatibility with PyTorch's computation graph.

Signed-off-by: samet-akcay <[email protected]>

* fix(model): update anomaly map generation to use torch tensors for calculations

This commit modifies the anomaly map generation logic to utilize PyTorch tensors instead of NumPy arrays for various calculations. This change enhances compatibility with the PyTorch computation graph and improves performance by leveraging GPU acceleration. Key updates include the conversion of statistical calculations and tensor operations to use PyTorch functions, ensuring consistency in tensor handling throughout the code.

Signed-off-by: samet-akcay <[email protected]>

* refactor(model): enhance anomaly map generation with PyTorch for statistical calculations

This commit refactors the anomaly map generation logic to replace NumPy-based statistical calculations with PyTorch equivalents, specifically using the  distribution for computing tau. Additionally, it improves precision handling by allowing the use of float64 in high precision mode. The changes streamline the computation process and maintain compatibility with the PyTorch computation graph.

Signed-off-by: samet-akcay <[email protected]>

* chore(license): update license year

Signed-off-by: samet-akcay <[email protected]>

* fix(download): enhance URL validation and update download logic

This commit improves the URL validation in the download function to ensure only http and https schemes are allowed. Additionally, it adds comments to clarify the safety of using  under these conditions, enhancing code readability and security awareness.

Signed-off-by: samet-akcay <[email protected]>

* 📝 chore(changelog): update changelog for v2.2.0 release with added features and fixes

* 🐛 fix(version): update version from 2.2.0dev to 2.2.0

* Update CHANGELOG.md

Signed-off-by: Ashwin Vaidya <[email protected]>

* Update changelog

Signed-off-by: Ashwin Vaidya <[email protected]>

* Use full PR links

Signed-off-by: Ashwin Vaidya <[email protected]>

* Add authors in changelog

Signed-off-by: Ashwin Vaidya <[email protected]>

* Update CHANGELOG.md

Co-authored-by: Copilot <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>

---------

Signed-off-by: samet-akcay <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: Ashwin Vaidya <[email protected]>
Co-authored-by: Ashwin Vaidya <[email protected]>
Co-authored-by: Ashwin Vaidya <[email protected]>
Co-authored-by: Copilot <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@ashwinvaidya17 @StarPlatinum7
🔧 docs(changelog): Fix entries (#3008)
d68a295 
* Remove duplicate entry

Signed-off-by: Ashwin Vaidya <[email protected]>

* Add missing entry

Signed-off-by: Ashwin Vaidya <[email protected]>

---------

Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@ashwinvaidya17 @StarPlatinum7
🔧 chore(version): Update main version to dev (#3010)
5831095 
Update version

Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
📦 docs(README): Update ReadMe for V2.2.0 release (#3017)
038ea18 
📦 update(README): Announce v2.2.0 release with new datasets, metrics, and performance improvements

Signed-off-by: StarPlatinum7 <[email protected]>
maxxgx and others added 14 commits November 6, 2025 19:32
@maxxgx @StarPlatinum7
🐛 fix(metrics): disable mps for torch metrics (#3019)
b1de175 
🐛 fix(metrics): disable mps for torch metrics (#3018)


* move to cpu when device is mps



---------

Signed-off-by: Ma, Xiangxiang <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
✨ feat(post-processing): Make minor changes as per comments
d40a7e5 
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
📦 docs(post-processor): revert docs for MEBIN
66e8335 
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
Update src/anomalib/post_processing/mebin_post_processor.py
36cf7dd 
Co-authored-by: Copilot <[email protected]>
Signed-off-by: Rajesh Gangireddy <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
Update src/anomalib/metrics/threshold/mebin.py
4cc8eb2 
Co-authored-by: Copilot <[email protected]>
Signed-off-by: Rajesh Gangireddy <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
Update src/anomalib/post_processing/mebin_post_processor.py
9328852 
Co-authored-by: Copilot <[email protected]>
Signed-off-by: Rajesh Gangireddy <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(mebin): remove debug print statement for value range
0732e13 
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(mebin): update threshold return types to float and remove debug…
b165722 
… print statement

Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(mebin): update return types in MEBin methods to tuples for bett…
c9abdab 
…er clarity

Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(mebin): simplify max calculation for connected component counts
6ce4d91 
Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(mebin): update examples in MEBin and MEBinPostProcessor for cla…
e139a6a 
…rity

Signed-off-by: StarPlatinum7 <[email protected]>
@rajeshgangireddy @StarPlatinum7
🐛 fix(mebin): refactor MEBin post-processing . Works now. Need to re-…
c071cad 
…check if implementation matches author's implementation

Signed-off-by: StarPlatinum7 <[email protected]>
@ashwinvaidya17 @StarPlatinum7
🔧 chore(codeowners): Update owners (#3042)
f2dd3dc 
Update CODEOWNERS

Signed-off-by: Ashwin Vaidya <[email protected]>
Signed-off-by: StarPlatinum7 <[email protected]>
@StarPlatinum7
pr-3030
9cfa779 
Signed-off-by: StarPlatinum7 <[email protected]>
AlexanderBarabanov
AlexanderBarabanov reviewed Nov 6, 2025
View reviewed changes
.github/actions/security/semgrep/action.yaml
--error \
--timeout "$INPUTS_TIMEOUT" \
--metrics=off \
--exclude "uv.lock" \
Copy link
Contributor

@AlexanderBarabanov AlexanderBarabanov Nov 6, 2025

Choose a reason for hiding this comment

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

Please rebase you PR as we removed this action (in #3014) and currenly use action from geti-ci.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@AlexanderBarabanov AlexanderBarabanov AlexanderBarabanov left review comments

@samet-akcay samet-akcay Awaiting requested review from samet-akcay samet-akcay is a code owner

@ashwinvaidya17 ashwinvaidya17 Awaiting requested review from ashwinvaidya17 ashwinvaidya17 is a code owner

@rajeshgangireddy rajeshgangireddy Awaiting requested review from rajeshgangireddy rajeshgangireddy is a code owner

@mramotowski mramotowski Awaiting requested review from mramotowski mramotowski is a code owner

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

10 participants

@StarPlatinum7 @AlexanderBarabanov @alfieroddan @abc-125 @rajeshgangireddy @kamillipka @samet-akcay @ashwinvaidya17 @monzelr @maxxgx