CHANGELOG.md

Changelog

All notable changes to this project will be documented in this file.

The format is based on Keep a Changelog.

[v0.7.0] - 2023-08-28

Added

• AUPRO binning capability by @yann-cv in open-edge-platform#1145
• Add support for receiving dataset paths as a list by @harimkang in open-edge-platform#1265
• Add modelAPI compatible OpenVINO export by @ashwinvaidya17 in open-edge-platform#1219

Changed

• Enable training with only normal images for MVTec by @djdameln in open-edge-platform#1241
• Improve default settings of EfficientAD in open-edge-platform#1143
• Added the tracer_kwargs to the TorchFXFeatureExtractor class by @JoaoGuibs in open-edge-platform#1214
• Replace cdist in Patchcore by @blaz-r in open-edge-platform#1267
• Ignore hidden directories when creating Folder dataset by @samet-akcay in open-edge-platform#1268

Fixed

• Fix typechecking error for toch.onnx.export by @ORippler in open-edge-platform#1159
• Fix benchmarking type error by @blaz-r in open-edge-platform#1155
• Fix incorrect shape mismatch between anomaly map and ground truth mask by @alexriedel1 in open-edge-platform#1182
• Fix dataset keys in benchmarking notebook by @samet-akcay in open-edge-platform#1242
• Remove config from argparse in OpenVINO inference script by @samet-akcay in open-edge-platform#1257
• Fix EfficientAD number of steps for optimizer lr change by @samet-akcay in open-edge-platform#1266
• Fix unable to read the mas image by @samet-akcay in open-edge-platform#1277

[v0.6.0] - 2023-06-15

Added

• EfficientAD by @alexriedel1 in open-edge-platform#1073
• AI-VAD bbox post-processing by @djdameln in open-edge-platform#1103
• Add dataset categories to data modules by @samet-akcay in open-edge-platform#1105
• Pass codedov token from environment by @ashwinvaidya17 in open-edge-platform#1102

Changed

• OV API2.0 by @paularamo in open-edge-platform#1098

Deprecated

• OV API1.0 by @paularamo in open-edge-platform#1098

 Fixed

• Fix Fastflow ONNX export. by @jasonvanzelm in open-edge-platform#1108
• Fix tile import typo by @xbkaishui in open-edge-platform#1106
• Fix pre-commit issues caused by the EfficientAD PR by @samet-akcay in open-edge-platform#1114
• Bump requests from 2.26.0 to 2.31.0 in /requirements by @dependabot in open-edge-platform#1100

New Contributors

• @xbkaishui made their first contribution in open-edge-platform#1106
• @jasonvanzelm made their first contribution in open-edge-platform#1108

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v0.5.1...v0.6.0

[v0.5.1] - 2023-05-24

Added

• 🧪 Add tests for tools by @ashwinvaidya17 in open-edge-platform#1069
• Add kolektor dataset by @Ravindu987 in open-edge-platform#983

Changed

• Rename metadata_path to metadata in OpenvinoInferencer in open-edge-platform#1101
• 📝 [Notebooks] - Simplify the dobot notebooks. by @samet-akcay in open-edge-platform#1084
• Upgrade python to 3.10 by @samet-akcay in open-edge-platform#1035
• 📝 [Notebooks] - Install anomalib via pip in the Jupyter Notebooks by @samet-akcay in open-edge-platform#1091
• Update code-scan workflow to use Trivy by @yunchu in open-edge-platform#1097

Fixed

• Fix init_state_dict bug in wrap_nncf_model in open-edge-platform#1101
• Fix mypy pep561 by @WenjingKangIntel in open-edge-platform#1088
• 📝 [Notebooks] Fix the broken formatting by @samet-akcay in open-edge-platform#1090

[v0.5.0] - 2023-05-09

Added

• 📚 Add OpenVINO Inference to getting started notebook. by @samet-akcay in open-edge-platform#897
• Mvtec 3d by @alexriedel1 in open-edge-platform#907
• MVTec 3D and Folder3D by @alexriedel1 in open-edge-platform#942
• add reorder=True argument in aupro by @triet1102 in open-edge-platform#944
• always reorder inputs when computing AUROC by @djdameln in open-edge-platform#945
• always reorder for aupr metric by @triet1102 in open-edge-platform#975
• Add README.md files to notebooks directories and its subdirectories (open-edge-platform#993)
• Set transformations from the config file by @alexriedel1 in open-edge-platform#990
• Add contributors to README.md by @samet-akcay in open-edge-platform#995
• Add codeowners file by @samet-akcay in open-edge-platform#1019
• Configure reference frame for multi-frame video clips by @djdameln in open-edge-platform#1023
• [Algo] Attribute-based Representations for Accurate and Interpretable Video Anomaly Detection by @djdameln in open-edge-platform#1040

Changed

• Switch to src layout by @samet-akcay in open-edge-platform#921
• Remove config flag from OpenVINOInferencer (open-edge-platform#939)
• Add ruff as the main linter by @samet-akcay in open-edge-platform#936
• Add a new workflow for code scanning by @yunchu in open-edge-platform#940
• Enable bandit scanning by @yunchu in open-edge-platform#954
• 🐳 Update Containers and Readme by @ashwinvaidya17 in open-edge-platform#952
• Refactor AUPRO metric by @triet1102 in open-edge-platform#991
• enable auto-fixing for ruff in pre-commit by @djdameln in open-edge-platform#1004
• Refactor strings and ints into enum.Enum by @WenjingKangIntel in open-edge-platform#1044
• Modify codecov upload by @ashwinvaidya17 in open-edge-platform#1080

Deprecated

• Remove torchvision and torchtext by @samet-akcay in open-edge-platform#903
• Remove codacy from ci docs by @ashwinvaidya17 in open-edge-platform#924
• Remove config dependency from OpenVINOInferencer by @samet-akcay in open-edge-platform#939
• Remove config from torch inferencer by @samet-akcay in open-edge-platform#1001

 Fixed

• Bugfix code logic to allow for passing of nn.Module to TorchFXFeatureExtractor by @ORippler in open-edge-platform#935
• fix broken links to tutorials (ex guides) by @sergiev in open-edge-platform#957
• Fixed outdated info in readme by @blaz-r in open-edge-platform#969
• Fix ruff isort integration by @samet-akcay in open-edge-platform#976
• Fix/samples dataframe annotation by @samet-akcay in open-edge-platform#981
• Fixed openvino_inferencer in gradio_inference by @blaz-r in open-edge-platform#972
• Fix issue in tutorial by @Ravindu987 in open-edge-platform#997
• Fix tarfile vulnerability by @djdameln in open-edge-platform#1003
• Cuda 11.4 dockerfile fix by @phcarval in open-edge-platform#1021
• Make anomalib PEP 561 compliant for mypy by @WenjingKangIntel in open-edge-platform#1038
• [Bug: 839] Crop in SSPCAB implementation by @isaacncz in open-edge-platform#1057
• [Bug: 865] datamodule.setup() assertion failed by @isaacncz in open-edge-platform#1058
• Fix logger message for test_split_ratio by @ugotsoul in open-edge-platform#1071
• Fix notebook readme formatting by @samet-akcay in open-edge-platform#1075

New Contributors

• @triet1102 made their first contribution in open-edge-platform#944
• @sergiev made their first contribution in open-edge-platform#957
• @blaz-r made their first contribution in open-edge-platform#969
• @ineiti made their first contribution in open-edge-platform#987
• @Ravindu987 made their first contribution in open-edge-platform#997
• @phcarval made their first contribution in open-edge-platform#1021
• @WenjingKangIntel made their first contribution in open-edge-platform#1038
• @isaacncz made their first contribution in open-edge-platform#1057
• @ugotsoul made their first contribution in open-edge-platform#1071

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v0.4.0...v0.5.0

[v0.4.0] - 2023-03-01

Added

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

Changed

• Configure reference frame for multi-frame video clips (open-edge-platform#1023)
• Bump OpenVINO version to 2022.3.0 (open-edge-platform#932)
• Remove the dependecy on a specific torchvision and torchmetrics packages.
• Bump PyTorch Lightning version to v.1.9.* (open-edge-platform#870)
• Make input image normalization and center cropping configurable from config (open-edge-platform#822)
• Improve flexibility and configurability of subset splitting (open-edge-platform#822)
• Switch to new datamodules design (open-edge-platform#822)
• Make normalization and center cropping configurable through config (open-edge-platform#795)
• Switch to new changelog format. (open-edge-platform#777)
• Rename feature to task (open-edge-platform#769)
• make device configurable in OpenVINO inference (open-edge-platform#755)
• 🚨 Fix torchmetrics version (open-edge-platform#754)
• Improve NNCF initilization (open-edge-platform#740)
• Migrate markdownlint + issue templates (open-edge-platform#738)
• 🐞 Patch Timm Feature Extractor (open-edge-platform#714)
• Padim arguments improvements (open-edge-platform#664)
• 📊 Update DFM results (open-edge-platform#674)
• Optimize anomaly score calculation for PatchCore (open-edge-platform#633)

Deprecated

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

Fixed

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

[v0.3.7] - 2022-10-28

What's Changed

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

New Contributors

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

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v0.3.6...v0.3.7

[v.0.3.6] - 2022-09-02

What's Changed

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

New Contributors

• @ashishbdatta made their first contribution in open-edge-platform#482
• @jingt2ch made their first contribution in open-edge-platform#514

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v0.3.5...v0.3.6

[v.0.3.5] - 2022-08-02

What's Changed

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

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v0.3.4...v0.3.5

[v.0.3.4] - 2022-08-01

What's Changed

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

New Contributors

• @ORippler made their first contribution in open-edge-platform#417
• @jeongHwarr made their first contribution in open-edge-platform#404

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/0.3.3...0.3.4

[v.0.3.3] - 2022-07-05

What's Changed

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

New Contributors

• @innat made their first contribution in open-edge-platform#382
• @VdLMV made their first contribution in open-edge-platform#392

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v.0.3.2...v.0.3.3

[v.0.3.2] - 2022-06-09

What's Changed

• Refactor AnomalyModule and LightningModules to explicitly define class arguments. by @samet-akcay in open-edge-platform#315
• 🐞 Fix inferencer in Gradio by @ashwinvaidya17 in open-edge-platform#332
• fix too many open images warning by @djdameln in open-edge-platform#334
• Upgrade wandb version by @ashwinvaidya17 in open-edge-platform#340
• Minor fix: Update folder dataset + notebooks link by @ashwinvaidya17 in open-edge-platform#338
• Upgrade TorchMetrics version by @djdameln in open-edge-platform#342
• 🚀 Set pylint version in tox.ini by @ashwinvaidya17 in open-edge-platform#345
• Add metrics configuration callback to benchmarking by @ashwinvaidya17 in open-edge-platform#346
• ➕ Add FastFlow Model by @samet-akcay in open-edge-platform#336
• ✨ Add toy dataset to the repository by @ashwinvaidya17 in open-edge-platform#350
• Add DRAEM Model by @djdameln in open-edge-platform#344
• 📃Update documentation by @ashwinvaidya17 in open-edge-platform#280
• 🏷️ Refactor Datamodule names by @samet-akcay in open-edge-platform#354
• ✨ Add Reverse Distillation by @ashwinvaidya17 in open-edge-platform#343

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v.0.3.1...v.0.3.2

[v.0.3.1] - 2022-05-17

What's Changed

• 🔧 Properly assign values to dataframe in folder dataset. by @samet-akcay in open-edge-platform#272
• ➕ Add warnings ⚠️ for inproper task setting in config files. by @samet-akcay in open-edge-platform#274
• Updated CHANGELOG.md by @samet-akcay in open-edge-platform#276
• ➕ Add long description to setup.py to make README.md PyPI friendly. by @samet-akcay in open-edge-platform#279
• ✨ Add hash check to data download by @ashwinvaidya17 in open-edge-platform#284
• ➕ Add Gradio by @julien-blanchon in open-edge-platform#283
• 🔨 Fix nncf key issue in nightly job by @ashwinvaidya17 in open-edge-platform#238
• Visualizer improvements pt1 by @djdameln in open-edge-platform#293
• 🧪 Fix nightly by @ashwinvaidya17 in open-edge-platform#299
• 🧪 Add tests for benchmarking script by @ashwinvaidya17 in open-edge-platform#297
• ➕ add input_info to nncf config when not defined by user by @djdameln in open-edge-platform#307
• 🐞 Increase tolerance + nightly path fix by @ashwinvaidya17 in open-edge-platform#318
• ➕ Add jupyter notebooks directory and first tutorial for getting-started by @samet-akcay in open-edge-platform#292

New Contributors

• @julien-blanchon made their first contribution in open-edge-platform#283

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v0.3.0...v.0.3.1

[v.0.3.0] - 2022-04-25

What's Changed

• 🛠 ⚠️ Fix configs to properly use pytorch-lightning==1.6 with GPU by @samet-akcay in open-edge-platform#234
• 🛠 Fix get_version in setup.py to avoid hard-coding version. by @samet-akcay in open-edge-platform#229
• 🐞 Fix image loggers by @ashwinvaidya17 in open-edge-platform#233
• Configurable metrics by @djdameln in open-edge-platform#230
• Make OpenVINO throughput optional in benchmarking by @ashwinvaidya17 in open-edge-platform#239
• 🔨 Minor fix: Ensure docs build runs only on isea-server by @ashwinvaidya17 in open-edge-platform#245
• 🏷 Rename --model_config_path to config by @samet-akcay in open-edge-platform#246
• Revert "🏷 Rename --model_config_path to config" by @samet-akcay in open-edge-platform#247
• ➕ Add --model_config_path deprecation warning to inference.py by @samet-akcay in open-edge-platform#248
• Add console logger by @samet-akcay in open-edge-platform#241
• Add segmentation mask to inference output by @ashwinvaidya17 in open-edge-platform#242
• 🛠 Fix broken mvtec link, and split url to fit to 120 by @samet-akcay in open-edge-platform#264
• 🛠 Fix mask filenames in folder dataset by @samet-akcay in open-edge-platform#249

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v0.2.6...v0.3.0

[v.0.2.6] - 2022-04-12

What's Changed

• ✏️ Add torchtext==0.9.1 to support Kaggle environments. by @samet-akcay in open-edge-platform#165
• 🛠 Fix KeyError:'label' in classification folder dataset by @samet-akcay in open-edge-platform#175
• 📝 Added MVTec license to the repo by @samet-akcay in open-edge-platform#177
• load best model from checkpoint by @djdameln in open-edge-platform#195
• Replace SaveToCSVCallback with PL CSVLogger by @samet-akcay in open-edge-platform#198
• WIP Refactor test by @ashwinvaidya17 in open-edge-platform#197
• 🔧 Dockerfile enhancements by @LukasBommes in open-edge-platform#172
• 🛠 Fix visualization issue for fully defected images by @djdameln in open-edge-platform#194
• ✨ Add hpo search using wandb by @ashwinvaidya17 in open-edge-platform#82
• Separate train and validation transformations by @alexriedel1 in open-edge-platform#168
• 🛠 Fix docs workflow by @ashwinvaidya17 in open-edge-platform#200
• 🔄 CFlow: Switch soft permutation to false by default to speed up training. by @samet-akcay in open-edge-platform#201
• Return only image, path and label for classification tasks in Mvtec and Btech datasets. by @samet-akcay in open-edge-platform#196
• 🗑 Remove freia as dependency and include it in anomalib/models/components by @samet-akcay in open-edge-platform#174
• Visualizer show classification and segmentation by @alexriedel1 in open-edge-platform#178
• ↗️ Bump up pytorch-lightning version to 1.6.0 or higher by @samet-akcay in open-edge-platform#193
• 🛠 Refactor DFKDE model by @ashwinvaidya17 in open-edge-platform#207
• 🛠 Minor fixes: Update callbacks to AnomalyModule by @ashwinvaidya17 in open-edge-platform#208
• 🛠 Minor update: Update pre-commit docs by @ashwinvaidya17 in open-edge-platform#206
• ✨ Directory streaming by @ashwinvaidya17 in open-edge-platform#210
• ✏️ Updated documentation for development on Docker by @LukasBommes in open-edge-platform#217
• 🏷 Fix Mac M1 dependency conflicts by @dreaquil in open-edge-platform#158
• 🐞 Set tiling off in pathcore to correctly reproduce the stats. by @samet-akcay in open-edge-platform#222
• 🐞fix support for non-square images by @ashwinvaidya17 in open-edge-platform#204
• Allow specifying feature layer and pool factor in DFM by @nahuja-intel in open-edge-platform#215
• 📝 Add GANomaly metrics to readme by @ashwinvaidya17 in open-edge-platform#224
• ↗️ Bump the version to 0.2.6 by @samet-akcay in open-edge-platform#223
• 📝 🛠 Fix inconsistent benchmarking throughput/time by @ashwinvaidya17 in open-edge-platform#221
• assign test split for folder dataset by @alexriedel1 in open-edge-platform#220
• 🛠 Refactor model implementations by @djdameln in open-edge-platform#225

New Contributors

• @LukasBommes made their first contribution in open-edge-platform#172
• @dreaquil made their first contribution in open-edge-platform#158
• @nahuja-intel made their first contribution in open-edge-platform#215

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v.0.2.5...v0.2.6

[v.0.2.5] - 2022-03-25

What's Changed

• Bugfix: fix random val/test split issue by @djdameln in open-edge-platform#48
• Fix Readmes by @ashwinvaidya17 in open-edge-platform#46
• Updated changelog by @samet-akcay in open-edge-platform#49
• add distinction between image and pixel threshold in postprocessor by @djdameln in open-edge-platform#50
• Fix docstrings by @ashwinvaidya17 in open-edge-platform#22
• Fix networkx requirement by @LeonidBeynenson in open-edge-platform#52
• Add min-max normalization by @djdameln in open-edge-platform#53
• Change hardcoded dataset path to environ variable by @ashwinvaidya17 in open-edge-platform#51
• Added cflow algorithm by @blakshma in open-edge-platform#47
• perform metric computation on cpu by @djdameln in open-edge-platform#64
• Fix Inferencer by @ashwinvaidya17 in open-edge-platform#60
• Updated readme for cflow and change default config to reflect results by @blakshma in open-edge-platform#68
• Fixed issue with model loading by @blakshma in open-edge-platform#69
• Docs/sa/fix readme by @samet-akcay in open-edge-platform#71
• Updated coreset subsampling method to improve accuracy by @blakshma in open-edge-platform#73
• Revert "Updated coreset subsampling method to improve accuracy" by @samet-akcay in open-edge-platform#79
• Replace SupportIndex with int by @samet-akcay in open-edge-platform#76
• Added reference to official CFLOW repo by @blakshma in open-edge-platform#81
• Fixed issue with k_greedy method by @blakshma in open-edge-platform#80
• Fix Mix Data type issue on inferencer by @samet-akcay in open-edge-platform#77
• Create CODE_OF_CONDUCT.md by @samet-akcay in open-edge-platform#86
• ✨ Add GANomaly by @ashwinvaidya17 in open-edge-platform#70
• Reorder auc only when needed by @djdameln in open-edge-platform#91
• Bump up the pytorch lightning to master branch due to vulnurability issues by @samet-akcay in open-edge-platform#55
• 🚀 CI: Nightly Build by @ashwinvaidya17 in open-edge-platform#66
• Refactor by @ashwinvaidya17 in open-edge-platform#87
• Benchmarking Script by @ashwinvaidya17 in open-edge-platform#17
• 🐞 Fix tensor detach and gpu count issues in benchmarking script by @ashwinvaidya17 in open-edge-platform#100
• Return predicted masks in predict step by @djdameln in open-edge-platform#103
• Add Citation to the Readme by @samet-akcay in open-edge-platform#106
• Nightly build by @ashwinvaidya17 in open-edge-platform#104
• c_idx cast to LongTensor in random sparse projection by @alexriedel1 in open-edge-platform#113
• Update Nightly by @ashwinvaidya17 in open-edge-platform#126
• Updated logos by @samet-akcay in open-edge-platform#131
• Add third-party-programs.txt file and update license by @LeonidBeynenson in open-edge-platform#132
• 🔨 Increase inference + openvino support by @ashwinvaidya17 in open-edge-platform#122
• Fix/da/image size bug by @djdameln in open-edge-platform#135
• Fix/da/image size bug by @djdameln in open-edge-platform#140
• optimize compute_anomaly_score by using torch native funcrtions by @alexriedel1 in open-edge-platform#141
• Fix IndexError in adaptive threshold computation by @djdameln in open-edge-platform#146
• Feature/data/btad by @samet-akcay in open-edge-platform#120
• Update for nncf_task by @AlexanderDokuchaev in open-edge-platform#145
• fix non-adaptive thresholding bug by @djdameln in open-edge-platform#152
• Calculate feature map shape patchcore by @alexriedel1 in open-edge-platform#148
• Add transform_config to the main config.yaml file. by @samet-akcay in open-edge-platform#156
• Add Custom Dataset Training Support by @samet-akcay in open-edge-platform#154
• Added extension as an option when saving the result images. by @samet-akcay in open-edge-platform#162
• Update anomalib version and requirements by @samet-akcay in open-edge-platform#163

New Contributors

• @LeonidBeynenson made their first contribution in open-edge-platform#52
• @blakshma made their first contribution in open-edge-platform#47
• @alexriedel1 made their first contribution in open-edge-platform#113
• @AlexanderDokuchaev made their first contribution in open-edge-platform#145

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v.0.2.4...v.0.2.5

[v.0.2.4] - 2021-12-22

What's Changed

• Bump up the version to 0.2.4 by @samet-akcay in open-edge-platform#45
• fix heatmap color scheme by @djdameln in open-edge-platform#44

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v.0.2.3...v.0.2.4

[v.0.2.3] - 2021-12-23

What's Changed

• Address docs build failing issue by @ashwinvaidya17 in open-edge-platform#39
• Fix docs pipeline 📄 by @ashwinvaidya17 in open-edge-platform#41
• Feature/dick/anomaly score normalization by @djdameln in open-edge-platform#35
• Shuffle train dataloader by @samet-akcay in open-edge-platform#42

Full Changelog: https://github.com/openvinotoolkit/anomalib/compare/v0.2.2...v.0.2.3

[v0.2.0 Pre-release] - 2021-12-14

What's Changed

• Address compatibility issues with OTE, that are caused by the legacy code. by @samet-akcay in #24
• Initial docs string by @ashwinvaidya17 in #9
• Load model did not work correctly as DFMModel did not inherit by @ashwinvaidya17 in #5
• Refactor/samet/data by @samet-akcay in #8
• Delete make.bat by @samet-akcay in #11
• TorchMetrics by @djdameln in #7
• ONNX node naming by @djdameln in #13
• Add FPS counter to TimerCallback by @ashwinvaidya17 in #12

Contributors

• @ashwinvaidya17
• @djdameln
• @samet-akcay

Full Changelog: https://github.com/openvinotoolkit/anomalib/commits/v0.2.0