v0.4.0

What's Changed

Added

• Add Dobot notebook (#928)
• Add ShanghaiTech Campus video anomaly detection dataset (#869)
• Add pyupgrade to pre-commit configs, and refactor based on pyupgrade and refurb (#845)
• Add CFA model implementation (#783)
• Add RKDE model implementation (#821)
• Add Visual Anomaly (VisA) dataset adapter (#824)
• Add Synthetic anomalous dataset for validation and testing (#822)
• Add Detection task type support (#822)
• Add UCSDped and Avenue dataset implementation (#822)
• Add base classes for video dataset and video datamodule (#822)
• Add base classes for image dataset and image dataModule (#822)
• ✨ Add CSFlow model (#657)
• Log loss for existing trainable models (#804)
• Add section for community project (#768)
• ✨ Add torchfx feature extractor (#675)
• Add tiling notebook (#712)
• Add posargs to tox to enable testing a single file (#695)
• Add option to load metrics with kwargs (#688)
• 🐞 Add device flag to TorchInferencer (#601)

Changed

• Bump OpenVINO version to 2022.3.0 (#932)
• Remove the dependecy on a specific torchvision and torchmetrics packages.
• Bump PyTorch Lightning version to v.1.9.* (#870)
• Make input image normalization and center cropping configurable from config (#822)
• Improve flexibility and configurability of subset splitting (#822)
• Switch to new datamodules design (#822)
• Make normalization and center cropping configurable through config (#795)
• Switch to new changelog format. (#777)
• Rename feature to task (#769)
• make device configurable in OpenVINO inference (#755)
• 🚨 Fix torchmetrics version (#754)
• Improve NNCF initilization (#740)
• Migrate markdownlint + issue templates (#738)
• 🐞 Patch Timm Feature Extractor (#714)
• Padim arguments improvements (#664)
• 📊 Update DFM results (#674)
• Optimize anomaly score calculation for PatchCore (#633)

Deprecated

• Deprecated PreProcessor class (#795)
• Deprecate OptimalF1 metric in favor of AnomalyScoreThreshold and F1Score (#796)

Fixed

• Fix bug in anomalib/data/utils/image.py to check if the path is directory (#919)
• Fix bug in MVTec dataset download (#842)
• Add early stopping to CS-Flow model (#817)
• Fix remote container by removing version pinning in Docker files (#797)
• Fix PatchCore performance deterioration by reverting changes to Average Pooling layer (#791)
• Fix zero seed (#766)
• Fix #699 (#700)
• 🐞 Fix folder dataset for classification tasks (#708)
• Update torchmetrics to fix compute_on_cpu issue (#711)
• Correct folder mask path (#660)
• Fix >100% confidence issue for OpenVINO inference (#667)
• Update pre-commit links and some other minor fixes (#672)
• Fix black formatting issues. (#674)

New Contributors

• @jpcbertoldo made their first contribution in #660
• @tanemaki made their first contribution in #766
• @Jonas1302 made their first contribution in #771
• @yunchu made their first contribution in #885
• @strelka145 made their first contribution in #919

Full Changelog: v0.3.7...v0.4.0

Dobot Dataset and API

This is to release the assets for the Dobot The Magician, an education robot arm portable and capable to run various automation tasks. The release contains an API to control the robot and a sample dataset captured via the robot.

v0.4.0rc2

[v0.4.0rc2] - 2023-02-10

Added

• Add ShanghaiTech Campus video anomaly detection dataset (#869)
• Add pyupgrade to pre-commit configs, and refactor based on pyupgrade and refurb (#845)
• Add CFA model implementation (#783)
• Add RKDE model implementation (#821)
• Add Visual Anomaly (VisA) dataset adapter (#824)
• Add Synthetic anomalous dataset for validation and testing (#822)
• Add Detection task type support (#822)
• Add UCSDped and Avenue dataset implementation (#822)
• Add base classes for video dataset and video datamodule (#822)
• Add base classes for image dataset and image dataModule (#822)
• ✨ Add CSFlow model (#657)
• Log loss for existing trainable models (#804)
• Add section for community project (#768)
• ✨ Add torchfx feature extractor (#675)
• Add tiling notebook (#712)
• Add posargs to tox to enable testing a single file (#695)
• Add option to load metrics with kwargs (#688)
• 🐞 Add device flag to TorchInferencer (#601)

Changed

• Remove the dependecy on a specific torchvision and torchmetrics packages.
• Bump PyTorch Lightning version to v.1.9.* (#870)
• Make input image normalization and center cropping configurable from config (#822)
• Improve flexibility and configurability of subset splitting (#822)
• Switch to new datamodules design (#822)
• Make normalization and center cropping configurable through config (#795)
• Switch to new changelog format. (#777)
• Rename feature to task (#769)
• make device configurable in OpenVINO inference (#755)
• 🚨 Fix torchmetrics version (#754)
• Improve NNCF initilization (#740)
• Migrate markdownlint + issue templates (#738)
• 🐞 Patch Timm Feature Extractor (#714)
• Padim arguments improvements (#664)
• 📊 Update DFM results (#674)
• Optimize anomaly score calculation for PatchCore (#633)

Deprecated

• Deprecated PreProcessor class (#795)
• Deprecate OptimalF1 metric in favor of AnomalyScoreThreshold and F1Score (#796)

Fixed

• Fix bug in MVTec dataset download (#842)
• Add early stopping to CS-Flow model (#817)
• Fix remote container by removing version pinning in Docker files (#797)
• Fix PatchCore performance deterioration by reverting changes to Average Pooling layer (#791)
• Fix zero seed (#766)
• Fix #699 (#700)
• 🐞 Fix folder dataset for classification tasks (#708)
• Update torchmetrics to fix compute_on_cpu issue (#711)
• Correct folder mask path (#660)
• Fix >100% confidence issue for OpenVINO inference (#667)
• Update pre-commit links and some other minor fixes (#672)
• Fix black formatting issues. (#674)

Full Changelog: v0.4.0rc1...v0.4.0rc2

v0.4.0rc1

[v0.4.0rc1] - 2023-02-07

Added

• Add ShanghaiTech Campus video anomaly detection dataset (#869)
• Add pyupgrade to pre-commit configs, and refactor based on pyupgrade and refurb (#845)
• Add CFA model implementation (#783)
• Add RKDE model implementation (#821)
• Add Visual Anomaly (VisA) dataset adapter (#824)
• Add Synthetic anomalous dataset for validation and testing (#822)
• Add Detection task type support (#822)
• Add UCSDped and Avenue dataset implementation (#822)
• Add base classes for video dataset and video datamodule (#822)
• Add base classes for image dataset and image dataModule (#822)
• ✨ Add CSFlow model (#657)
• Log loss for existing trainable models (#804)
• Add section for community project (#768)
• ✨ Add torchfx feature extractor (#675)
• Add tiling notebook (#712)
• Add posargs to tox to enable testing a single file (#695)
• Add option to load metrics with kwargs (#688)
• 🐞 Add device flag to TorchInferencer (#601)

Changed

• Bump PyTorch Lightning version to v.1.9.* (#870)
• Make input image normalization and center cropping configurable from config (#822)
• Improve flexibility and configurability of subset splitting (#822)
• Switch to new datamodules design (#822)
• Make normalization and center cropping configurable through config (#795)
• Switch to new changelog format. (#777)
• Rename feature to task (#769)
• make device configurable in OpenVINO inference (#755)
• 🚨 Fix torchmetrics version (#754)
• Improve NNCF initilization (#740)
• Migrate markdownlint + issue templates (#738)
• 🐞 Patch Timm Feature Extractor (#714)
• Padim arguments improvements (#664)
• 📊 Update DFM results (#674)
• Optimize anomaly score calculation for PatchCore (#633)

Deprecated

• Deprecated PreProcessor class (#795)
• Deprecate OptimalF1 metric in favor of AnomalyScoreThreshold and F1Score (#796)

Fixed

• Fix bug in MVTec dataset download (#842)
• Add early stopping to CS-Flow model (#817)
• Fix remote container by removing version pinning in Docker files (#797)
• Fix PatchCore performance deterioration by reverting changes to Average Pooling layer (#791)
• Fix zero seed (#766)
• Fix #699 (#700)
• 🐞 Fix folder dataset for classification tasks (#708)
• Update torchmetrics to fix compute_on_cpu issue (#711)
• Correct folder mask path (#660)
• Fix >100% confidence issue for OpenVINO inference (#667)
• Update pre-commit links and some other minor fixes (#672)
• Fix black formatting issues. (#674)

New Contributors

• @yunchu made their first contribution in #885

RKDE Weights

This release adds the feature extractor weights for the RKDE model implementation.

v0.3.7

What's Changed

• Feature/comet logging by @sherpan in #517
• 🐞 Fix linting issues by @ashwinvaidya17 in #535
• 🐞 Bug Fix: Solve NaN values of anomaly scores for PatchCore model by @bsl546 in #549
• 🐞 Bug Fix: Help description for argument task by @youngquan in #547
• reutrn results of load_state_dict func by @zywvvd in #546
• 🔨 Pass pre-trained from config to ModelLightning by @samet-akcay in #529
• Benchmarking tool with Comet by @sherpan in #545
• Add map_location when loading the weights by @samet-akcay in #562
• Add patchcore to openvino export test + upgrade lightning by @ashwinvaidya17 in #565
• 🐞 Fix category check for folder dataset in anomalib CLI by @samet-akcay in #567
• Refactor PreProcessor and fix Visualizer denormalization issue. by @samet-akcay in #570
• 🔨 Check for successful openvino conversion by @ashwinvaidya17 in #571
• Comet HPO by @sherpan in #563
• Fix patchcore image-level score computation by @djdameln in #580
• Fix anomaly map computation in CFlow when batch size is 1. by @samet-akcay in #589
• Documentation refactor by @samet-akcay in #576
• ✨ Add notebook for hpo by @ashwinvaidya17 in #592
• 🐞 Fix comet HPO by @ashwinvaidya17 in #597
• ✨ Replace keys from benchmarking script by @ashwinvaidya17 in #595
• Update README.md by @Owaiskhan9654 in #623
• 🐳 Containerize CI by @ashwinvaidya17 in #616
• add deprecation warning to denormalize class by @djdameln in #629
• Anomalib CLI Improvements - Update metrics and create post_processing section in the config file by @samet-akcay in #607
• Convert adaptive_threshold to Enum in configs by @samet-akcay in #637
• Create meta_data.json with ONNX export as well as OpenVINO export by @calebmm in #636
• 🖌 refactor export callback by @ashwinvaidya17 in #640
• 🐞 Address docs build by @ashwinvaidya17 in #639
• Optimized inference with onnx for patchcore. by @acai66 in #652

New Contributors

• @sherpan made their first contribution in #517
• @bsl546 made their first contribution in #549
• @youngquan made their first contribution in #547
• @zywvvd made their first contribution in #546
• @Owaiskhan9654 made their first contribution in #623
• @calebmm made their first contribution in #636
• @acai66 made their first contribution in #652

Full Changelog: v0.3.6...v0.3.7

v0.3.6

What's Changed

• Add publish workflow + update references to main by @ashwinvaidya17 in #480
• Fix Dockerfile by @ORippler in #478
• Fix onnx export by rewriting GaussianBlur by @ORippler in #476
• DFKDE refactor to accept any layer name like other models by @ashishbdatta in #482
• 🐞 Log benchmarking results in sub folder by @ashwinvaidya17 in #483
• 🐞 Fix Visualization keys in new CLI by @ashwinvaidya17 in #487
• fix Perlin augmenter for non divisible image sizes by @djdameln in #490
• 📝 Update the license headers by @samet-akcay in #491
• change default parameter values for DRAEM by @djdameln in #495
• Add reset methods to metrics by @ashwinvaidya17 in #488
• Feature Extractor Refactor by @ashishbdatta in #451
• Convert AnomalyMapGenerator to nn.Module by @samet-akcay in #497
• Add github pr labeler to automatically label PRs by @samet-akcay in #498
• Add coverage by @ashwinvaidya17 in #499
• 🐞 Change if check by @ashwinvaidya17 in #501
• SSPCAB implementation by @djdameln in #500
• 🛠 Refactor Normalization by @ashwinvaidya17 in #496
• Enable generic exporting of a trained model to ONNX or OpenVINO IR by @ashishbdatta in #509
• Updated documentation to add examples for exporting model by @ashishbdatta in #515
• Ignore pixel metrics in classification task by @djdameln in #516
• Update export documentation by @djdameln in #521
• FIX: PaDiM didn't use config.model.pre_trained. by @jingt2ch in #514
• Reset adaptive threshold between epochs by @djdameln in #527
• Add PRO metric by @djdameln in #508
• Set full_state_update attribute in custom metrics by @djdameln in #531
• 🐞 Set normalization method from anomaly module by @ashwinvaidya17 in #530

New Contributors

• @ashishbdatta made their first contribution in #482
• @jingt2ch made their first contribution in #514

Full Changelog: v0.3.5...v0.3.6

v.0.3.5 - Minor bug-fix release

v.0.3.5 - 2022-08-02

What's Changed

• 🐞 Fix inference for draem by @djdameln in #470
• 🐞 🛠 Bug fix in the inferencer by @samet-akcay in #475

v0.3.4

What's Changed

• Add encoding to LONG_DESCRIPTION in setup.py by @samet-akcay in #419
• Fix visualization by @ORippler in #417
• Fix openvino circular import issue by @samet-akcay in #416
• Fix inferener arg names and weight path issue. by @samet-akcay in #422
• Remove the redundant loss_val by @samet-akcay in #425
• 📃 Add documentation for gradio inference by @ashwinvaidya17 in #427
• Add pre_train as a configurable parameter by @samet-akcay in #431
• 🛠 Fix config files and refactor dfkde by @samet-akcay in #435
• Add metric visualizations by @ORippler in #429
• Fix: data split issue by @jeongHwarr in #404
• 🚚 Move perlin noise to common folder by @ashwinvaidya17 in #424
• Support null seed by @ashwinvaidya17 in #437
• 🐞 Change if statement by @ashwinvaidya17 in #439
• Fix visualizer for classification, mode=simple by @ORippler in #442
• Feature/aupro test by @ORippler in #444
• Replace PyTorchLightning extras dependency by @ashwinvaidya17 in #455
• 🛠 Fix tox configuration by @samet-akcay in #446
• Ignore ipynb files to detect the repo language by @samet-akcay in #456
• Move configuration from tox to pyproject by @samet-akcay in #458
• Add Torch Inferencer and Update Openvino and Gradio Inferencers. by @samet-akcay in #453
• Address markdownlint issues by @samet-akcay in #460
• 🐞 Fix HPO by @ashwinvaidya17 in #462
• Remove docs requirements by @ashwinvaidya17 in #467
• Add codacy badge to readme by @samet-akcay in #468

New Contributors

• @ORippler made their first contribution in #417
• @jeongHwarr made their first contribution in #404

Full Changelog: 0.3.3...0.3.4

0.3.3

What's Changed

• Move initialization log message to base class by @djdameln in #363
• 🚚 Move logging from train.py to the getter functions by @samet-akcay in #365
• 🚜 Refactor loss computation by @djdameln in #364
• 📝 Add a technical blog post to explain how to run anomalib. by @ashwinvaidya17 in #359
• 📚 Add datamodule jupyter notebooks. by @samet-akcay in #357
• 📝 Add benchmarking notebook by @ashwinvaidya17 in #353
• ➕ Add PyPI downloads badge to the readme. by @samet-akcay in #370
• Update README.md by @innat in #382
• Create Anomalib CLI by @samet-akcay in #378
• 🛠 Fix configs to remove logging heatmaps from classification models. by @samet-akcay in #387
• Add FastFlow model training testing inference via Anomalib API by @samet-akcay in #386
• PaDim occasionally NaNs in anomaly map by @VdLMV in #392
• Inference + Visualization by @djdameln in #390

New Contributors

• @innat made their first contribution in #382
• @VdLMV made their first contribution in #392

Full Changelog: v.0.3.2...0.3.3