v0.3.0

What's Changed

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

Full Changelog: v0.2.6...v0.3.0

v0.2.6

What's Changed

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

New Contributors

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

Full Changelog: v.0.2.5...v0.2.6

v.0.2.5

What's Changed

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

New Contributors

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

Full Changelog: v.0.2.4...v.0.2.5

v0.2.4

What's Changed

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

Full Changelog: v.0.2.3...v.0.2.4

v.0.2.3

What's Changed

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

Full Changelog: v0.2.2...v.0.2.3

v0.2.2

What's Changed

• Add PR and Issue Templates by @samet-akcay in #30
• Organize anomalib dependencies by @samet-akcay in #32
• Limit parallel runners by @ashwinvaidya17 in #38
• Bump lxml from 4.6.3 to 4.6.5 in /requirements by @dependabot in #37

Full Changelog: v0.2.1...v0.2.2

v0.2.1

What's Changed

• Bump up anomalib version
• Docs/dick/root readme by @samet-akcay in #31
• Add wandb logger by @ashwinvaidya17 in #23

Full Changelog: v0.2.0...v0.2.1

v0.2.0

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

New Contributors

• @samet-akcay made their first contribution in #8
• @djdameln made their first contribution in #7

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