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