Super-gradients

This GitHub Release was done automatically by CircleCI

This GitHub Release was done automatically by CircleCI

New Features
* Added DistributedSamplerWrapper to automatically wrap non-dist samplers in cases we use dist mode by NatanBagrov in https://github.com/Deci-AI/super-gradients/pull/1856
* YoloNAS_Pose_Fine_Tuning_Animals_Pose_Dataset by ofrimasad in https://github.com/Deci-AI/super-gradients/pull/1876
* Introduce fp16 flag to enable/disable mixed precision for predict() by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1881
* Feature/sg 1386 granular control over export in ptq and qat by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1879

Deprecations
* Deprecate tight_box_rotation parameters in COCODetectionDataset by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1786

Improvements
* `pycocotools` dependency removed by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1791
* Added explicit antialias=False to ensure we can export torchvision Resize to ONNX by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1824
* Updated colab notebook to include line that initializes plugins by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1822
* Feature/sg 000 add note that qat only supports gpu by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1830
* Added more hydra resolvers by NatanBagrov in https://github.com/Deci-AI/super-gradients/pull/1829
* Added crash tip for the case when SGLogger is None by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1799
* Added YoloNAS-Pose fine-tuning notebook by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1831
* allow flexibility to provide absolute path to annotations by NatanBagrov in https://github.com/Deci-AI/super-gradients/pull/1840
* fix vulnerabilities by ofrimasad in https://github.com/Deci-AI/super-gradients/pull/1861
* fix onnx version by ofrimasad in https://github.com/Deci-AI/super-gradients/pull/1863
* fix tarfile extraction by ofrimasad in https://github.com/Deci-AI/super-gradients/pull/1868

Bugfixes
* fixed an issue with eval forcing to have a val_dataloader in config by NatanBagrov in https://github.com/Deci-AI/super-gradients/pull/1823
* Fix typo error in ann_areas vs ann_area attribute by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1828
* Added fixed random seed to not depend of randomness of initialized weights by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1839
* Fixed a wrong color channel order when processing images from webcamera and improved exception message when on MacOS by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1821
* Bugfix by ofrimasad in https://github.com/Deci-AI/super-gradients/pull/1874
* fix a bug when ploting a dataset with images in a range other than 0-255 by ofrimasad in https://github.com/Deci-AI/super-gradients/pull/1884
* Fixed speed of COCO dataset parsing by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1888

Other
* Update welcome.md by ofrimasad in https://github.com/Deci-AI/super-gradients/pull/1790
* Update README.md - voxel51 integration by Shani-Perl in https://github.com/Deci-AI/super-gradients/pull/1827
* fix vulnerability by ofrimasad in https://github.com/Deci-AI/super-gradients/pull/1872
* Bug/sg 1247 reoarganize tests by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1789
* Added warning message for dataset license by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1846

**Full Changelog**: https://github.com/Deci-AI/super-gradients/compare/3.6.0...3.6.1

Hey channel
We're pleased to announce the release of Super-Gradients 3.6.0 :slightly_smiling_face: .
This update includes several important changes and improvements:
Changes and Enhancements
- Added segmentation samples and support for albumentation transforms for segmentation, contributed by shaydeci.
- Implemented distance-based detection matching in `DetectionMetrics` as an enhancement by DimaBir.
- New training hyperparameter - finetune, and multiple LR assignment by shaydeci, read about it [here](https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/LRAssignment.md)
- Enhanced `ImagePermute` processing inclusion, by BloodAxe.
- Improved dataset plotting and plot functionality, by
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Updated prediction notebooks and documentation, thanks to
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Supported depth estimation dataset and added depth estimation metrics support, by shaydeci.
- Proposed an API for checking model input compatibility, by BloodAxe.
- Extended `predict()` support for segmentation models, by BloodAxe.
- Removed deprecated features from version 3.6.0, by shaydeci.
- Updated pre-trained models badge URL, contributed by gasparitiago.
- Made changes to `PPYoloELoss`, removing the requirement for a `reg_max` parameter, by BloodAxe.
- Switched to using `onnxsim` instead of `onnx-simplifier` for consistency in naming, thanks to BloodAxe.
Bugfixes
- Resolved a bug in `OhemLoss` thanks to danielafrimi.
- Updated conditions to ensure functionality only on rank 0 where `[context.sg](http://context.sg/)_logger` is available, by shaydeci.
- Modified the default `set_device` value to prevent unintentional launch of DDP, updated by
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Addressed a bug where `multigpu=None` with `device=cpu` wasn't functioning as expected, thanks to
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Adjusted bounding box thickness and text size relative to bbox size, for object detection model's predict() by
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Addressed a bug in `DetectionMixup` that affected `YoloXTrainingStageSwitchCallback`, by BloodAxe.
- Corrected a typo in an exception message variable name, by BloodAxe.
- Reintegrated tests and refined CI/CD workflows, thanks to shaydeci and Yonatan-Kaplounov.
- Fixed import issues and improved model flexibility and metrics handling, mainly by BloodAxe.
- Ensured class names in `DetectionDataset` are contained within a trivial container, by BloodAxe.
- Fixed `ExtremeBatchDetectionVisualizationCallback` for multiscale collate function, by BloodAxe.
- Several bug fixes and improvements in `DistanceBasedDetectionMetrics` and `DetectionMetrics`, by BloodAxe.
And various other fixes and improvements across the board to enhance functionality and user experience.
For a detailed list of changes, refer to the [full changelog](https://github.com/Deci-AI/super-gradients/compare/3.5.0...3.6.0).
New Contributors
- Welcome to the contributors' team, DimaBir, gasparitiago, and Yonatan-Kaplounov, for making their first contributions.Hey channel
We're pleased to announce the release of Super-Gradients 3.6.0 :slightly_smiling_face: .
This update includes several important changes and improvements:
Changes and Enhancements
- Added segmentation samples and support for albumentation transforms for segmentation, contributed by shaydeci.
- Implemented distance-based detection matching in `DetectionMetrics` as an enhancement by DimaBir.
- New training hyperparameter - finetune, and multiple LR assignment by shaydeci, read about it [here](https://github.com/Deci-AI/super-gradients/blob/master/documentation/source/LRAssignment.md)
- Enhanced `ImagePermute` processing inclusion, by BloodAxe.
- Improved dataset plotting and plot functionality, by
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Updated prediction notebooks and documentation, thanks to
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Supported depth estimation dataset and added depth estimation metrics support, by shaydeci.
- Proposed an API for checking model input compatibility, by BloodAxe.
- Extended `predict()` support for segmentation models, by BloodAxe.
- Removed deprecated features from version 3.6.0, by shaydeci.
- Updated pre-trained models badge URL, contributed by gasparitiago.
- Made changes to `PPYoloELoss`, removing the requirement for a `reg_max` parameter, by BloodAxe.
- Switched to using `onnxsim` instead of `onnx-simplifier` for consistency in naming, thanks to BloodAxe.
Bugfixes
- Resolved a bug in `OhemLoss` thanks to danielafrimi.
- Updated conditions to ensure functionality only on rank 0 where `[context.sg](http://context.sg/)_logger` is available, by shaydeci.
- Modified the default `set_device` value to prevent unintentional launch of DDP, updated by
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Addressed a bug where `multigpu=None` with `device=cpu` wasn't functioning as expected, thanks to
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Adjusted bounding box thickness and text size relative to bbox size, for object detection model's predict() by
[Louis Dupont](https://deciai.slack.com/team/U03FHLX8FH7)
.
- Addressed a bug in `DetectionMixup` that affected `YoloXTrainingStageSwitchCallback`, by BloodAxe.
- Corrected a typo in an exception message variable name, by BloodAxe.
- Reintegrated tests and refined CI/CD workflows, thanks to shaydeci and Yonatan-Kaplounov.
- Fixed import issues and improved model flexibility and metrics handling, mainly by BloodAxe.
- Ensured class names in `DetectionDataset` are contained within a trivial container, by BloodAxe.
- Fixed `ExtremeBatchDetectionVisualizationCallback` for multiscale collate function, by BloodAxe.
- Several bug fixes and improvements in `DistanceBasedDetectionMetrics` and `DetectionMetrics`, by BloodAxe.
And various other fixes and improvements across the board to enhance functionality and user experience.
For a detailed list of changes, refer to the [full changelog](https://github.com/Deci-AI/super-gradients/compare/3.5.0...3.6.0).
New Contributors
- Welcome to the contributors' team, DimaBir, gasparitiago, and Yonatan-Kaplounov, for making their first contributions..

This GitHub Release was done automatically by CircleCI

New features
* A `model.predict(video)` does not cause OOM anymore by hakuryuu96 in https://github.com/Deci-AI/super-gradients/pull/1621
* Learning rates can now be specified per-layer (Can now freeze layers or train backbone with lower LR) by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1612
* A `model.predict` can now take `skip_resize` argument to run forward in the original image resolution (Good for large images & small objects) by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1605
* Added support of multiple test loaders in train_from_config by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1641

Documentation
* Added documentation for DatasetAdapter by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1591
* Added notebook for adding a custom dataset by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1592
* Added notebooks on segmentation (quick start & transfer learning) by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1634
* Add notebook for fine-tuning YoloNAS with QAT by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1638

Bugfixes
* Fixed bug in quantized YoloNAS model that let do degraded performance of the _exported_ model by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1638
* Fix numpy deprecation warning on creating ragged array when using `_pad_image` by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1632
* Fixed bug in `model.export()` that led to crash when FP16 export was requested and model was on CPU device by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1643
* Fix Invalid syntax at convert_recipe_to_code.py by seunghalee1226 in https://github.com/Deci-AI/super-gradients/pull/1642
* Fixed bug that lead to incorrect visualization of target bboxes when using DetectionVisualization.visualize_batch by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1652
* Fixed bug in Data Adapter for Segmentation task by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1654


New Contributors
* seunghalee1226 made their first contribution in https://github.com/Deci-AI/super-gradients/pull/1642

**Full Changelog**: https://github.com/Deci-AI/super-gradients/compare/3.4.1...3.5.0

Bugfixes
* Fix serialization of ListConfig in checkpoint state dictionary by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1534
* Ensure that `checkpoint_num_classes` is propagated from YAML to model by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1533
* Fixed a bug in YoloNASPose.export() that prevented to export model for BS>1 by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1530
* Check class_id validity in DetectionDataset by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1536
* Fix training_params deprecation by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1542
* Fixing typos and adding extra info to CONTRIBUTING by hakuryuu96 in https://github.com/Deci-AI/super-gradients/pull/1546
* Remove `np.bool` which is not supported in latest np versions by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1558
* Fix `CSPDarknet53.foward` by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1564
* Bugfix of model.export() to work correct with bs>1 by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1551
* Mixed precision automatically changed with warning by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1567
* Updated data-gradients requirement by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1572
* Fixed issue with torch 1.12 where _scale_fn_ref is missing in CyclicLR by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1575
* Fixed issue with torch 1.12 issue with arange not supporting fp16 for CPU device. by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1574
* Reorder operators to ensure Neg operator is not used by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1584
* Updated "What are Recipes and How To Use Them" notebook by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1586
* Update link for "Open in Colab" by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1588
* Added metrics logging to checkpoint and separate yaml file by hakuryuu96 in https://github.com/Deci-AI/super-gradients/pull/1562
* Fixed bug in ModelWeightAveraging class that led to corrupted model when metric to watch was NaN/Inf by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1598
* Transfer learning classification notebook update by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1587
* Update KD Notebook for classification by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1595
* Fixed bug in COCOPoseEstimationDataset which caused the images or reversed channel order used in predict() by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1609
* Fixed supervisely .get which uses dataset: inside the .yaml file by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1603
* Fixed bug in _pad_image that did not support pad_value=(R,B,G) input by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1599
* Fixed ListConfig in pose estimation dataset classes by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1602
* Enforced check of that all notebooks has matching SG version installed by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1607
* Update README by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1615
* Way to fix bug with validation frequency by hakuryuu96 in https://github.com/Deci-AI/super-gradients/pull/1601
* Changed key for SegKDLoss by hakuryuu96 in https://github.com/Deci-AI/super-gradients/pull/1620
* Bump onnx-simplifier version require at least 0.4.3 by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1631

Enhancement:
* Add `class_names` to `model.predict` for detection by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1529
* Argument max_batches support to training log and tqdm progress bar. by hakuryuu96 in https://github.com/Deci-AI/super-gradients/pull/1554
* Add explanations on experiment management by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1559
* Added recipe unifying script by shaydeci in https://github.com/Deci-AI/super-gradients/pull/1560
* Added packages to pth checkpoint by hakuryuu96 in https://github.com/Deci-AI/super-gradients/pull/1581
* Added sequential assignment capability to PPYoloELoss by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1582
* Add replace in channels by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1557
* Add image examples by Louis-Dupont in https://github.com/Deci-AI/super-gradients/pull/1589
* Update ptq and qat training by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1618
* Added convert_from_recipe script, that converts yaml train_from_config, "recipe style" training script to a "python dictionaries" standalone training script. by BloodAxe in https://github.com/Deci-AI/super-gradients/pull/1568
New Contributors
* hakuryuu96 made their first contribution in https://github.com/Deci-AI/super-gradients/pull/1546
* aler9 made their first contribution in https://github.com/Deci-AI/super-gradients/pull/1548