Keras-cv

What's Changed
* Imagenet loading improvements suggested by sayakpaul by ianstenbit in https://github.com/keras-team/keras-cv/pull/774
* Add TPU support for basic_training by ianstenbit in https://github.com/keras-team/keras-cv/pull/757
* Add accelerator count to training history by ianstenbit in https://github.com/keras-team/keras-cv/pull/776
* Porting EfficientNets to KerasCV by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/740
* Promote model tests to integration by LukeWood in https://github.com/keras-team/keras-cv/pull/788
* Add pre-trained weights for DenseNet201 by ianstenbit in https://github.com/keras-team/keras-cv/pull/785
* Allow the KerasCV AnchorBox generator to work the `image_shape` instead of just images by LukeWood in https://github.com/keras-team/keras-cv/pull/790
* Add segmask support for RandomRotate by ianstenbit in https://github.com/keras-team/keras-cv/pull/780
* Add API to disable geometric transformations in RandAugment by LukeWood in https://github.com/keras-team/keras-cv/pull/792
* Some final touches to the RetinaNet API by LukeWood in https://github.com/keras-team/keras-cv/pull/784
* Step 1/2: refactor kerascv by tanzhenyu in https://github.com/keras-team/keras-cv/pull/791
* RandomFlip : added test for ragged bounding box by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/789
* Add segmask support for RandomResizedCrop by ianstenbit in https://github.com/keras-team/keras-cv/pull/777
* Add box matcher. by tanzhenyu in https://github.com/keras-team/keras-cv/pull/794
* Fixed samplers to support tensor shapes by quantumalaviya in https://github.com/keras-team/keras-cv/pull/798
* add reduction=none parameter to losses to fix retinanet detection example by akucia in https://github.com/keras-team/keras-cv/pull/796
* Update anchor_generator.py to fix docstring by LukeWood in https://github.com/keras-team/keras-cv/pull/800
* Fix bounding_box.clip_to_image() by LukeWood in https://github.com/keras-team/keras-cv/pull/802
* Add base feature pyramid network (FPN) to Keras CV by qlzh727 in https://github.com/keras-team/keras-cv/pull/803
* Add ROIGenerator. by tanzhenyu in https://github.com/keras-team/keras-cv/pull/804
* Add within 3d box detection. by tanzhenyu in https://github.com/keras-team/keras-cv/pull/787
* Add target gather as private API. by tanzhenyu in https://github.com/keras-team/keras-cv/pull/813
* Update docs for contrastive projector and probe by ianstenbit in https://github.com/keras-team/keras-cv/pull/814
* Add ROIPooler layer for RCNN. by tanzhenyu in https://github.com/keras-team/keras-cv/pull/808
* Setup initial benchmarks for model training by ianstenbit in https://github.com/keras-team/keras-cv/pull/810
* added the implementations of resnet 18 and 34 by zaccharieramzi in https://github.com/keras-team/keras-cv/pull/805
* Add classification head for segmentation model by qlzh727 in https://github.com/keras-team/keras-cv/pull/817
* add coordinate transform and spherical transform. by tanzhenyu in https://github.com/keras-team/keras-cv/pull/819
* Split RandomlyResizedCrop into two API surfaces (RandomlyZoomedCrop, RandomCropAndResize) by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/738
* Add ROISampler. by tanzhenyu in https://github.com/keras-team/keras-cv/pull/818
* Add Stable Diffusion by fchollet in https://github.com/keras-team/keras-cv/pull/828
* Add mixed precision support by LukeWood in https://github.com/keras-team/keras-cv/pull/834
* Stable diffusion small fixes by bhack in https://github.com/keras-team/keras-cv/pull/836
* Do image clipping in numpy space by fchollet in https://github.com/keras-team/keras-cv/pull/838

New Contributors
* akucia made their first contribution in https://github.com/keras-team/keras-cv/pull/796
* zaccharieramzi made their first contribution in https://github.com/keras-team/keras-cv/pull/805
* fchollet made their first contribution in https://github.com/keras-team/keras-cv/pull/828

**Full Changelog**: https://github.com/keras-team/keras-cv/compare/v0.3.2...v0.3.3

What's Changed
* Add tensorflow_datasets dep to Dockerfile by bhack in https://github.com/keras-team/keras-cv/pull/750
* Add all of the no-op segmentation mask augmentations by ianstenbit in https://github.com/keras-team/keras-cv/pull/751
* Promote anchor generator default to a public api by LukeWood in https://github.com/keras-team/keras-cv/pull/755
* Write steps_per_second in basic_training by ianstenbit in https://github.com/keras-team/keras-cv/pull/758
* Remove cd to keras_Cv by bhack in https://github.com/keras-team/keras-cv/pull/756
* Fix FocalLoss reduction, SmoothL1 reduction, and add extra loss validation to RetinaNet model by LukeWood in https://github.com/keras-team/keras-cv/pull/760
* Fix loss reduction in the RetinaNet trainstep by LukeWood in https://github.com/keras-team/keras-cv/pull/764
* Add integration tests to GCB by LukeWood in https://github.com/keras-team/keras-cv/pull/761
* Update object_detection_base_model.py by LukeWood in https://github.com/keras-team/keras-cv/pull/771
* SimCLR implementation by ianstenbit in https://github.com/keras-team/keras-cv/pull/699
* Remove the tensorflow_datasets as installation dep by qlzh727 in https://github.com/keras-team/keras-cv/pull/772
* Remove the tfds (typo) from the requirements.txt by qlzh727 in https://github.com/keras-team/keras-cv/pull/773
* Fix weight loading in RetinaNet and introduce unit tests to ensure weight loading works as intended by LukeWood in https://github.com/keras-team/keras-cv/pull/768
* Add segmask support for random_flip by ianstenbit in https://github.com/keras-team/keras-cv/pull/775


**Full Changelog**: https://github.com/keras-team/keras-cv/compare/v0.3.1...v0.3.2

What's Changed
* Improves `shell/format.sh` for local environment setups by atuleu in https://github.com/keras-team/keras-cv/pull/658
* Add v0 pre-trained weights for DenseNet169 by ianstenbit in https://github.com/keras-team/keras-cv/pull/660
* Restructure training scripts to avoid duplication by ianstenbit in https://github.com/keras-team/keras-cv/pull/659
* Introduce an Object Detection API to KerasCV by LukeWood in https://github.com/keras-team/keras-cv/pull/609
* Use aliasing for weights config to avoid duplicate weight files by ianstenbit in https://github.com/keras-team/keras-cv/pull/661
* Added no-op augment_bounding_boxes() methods by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/656
* Porting over RegNets from keras.applications by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/590
* Revert "Porting over RegNets from keras.applications (590)" by LukeWood in https://github.com/keras-team/keras-cv/pull/674
* applications -> models by LukeWood in https://github.com/keras-team/keras-cv/pull/683
* Add IoU loss by quantumalaviya in https://github.com/keras-team/keras-cv/pull/634
* Make initial learning rate flag-controlled in basic_training by ianstenbit in https://github.com/keras-team/keras-cv/pull/687
* Add a contribution guide for training scripts by ianstenbit in https://github.com/keras-team/keras-cv/pull/626
* Fix classes docstring to match code behavior by ianstenbit in https://github.com/keras-team/keras-cv/pull/689
* Add GPU-accelerated testing by ianstenbit in https://github.com/keras-team/keras-cv/pull/692
* Fix flag type for initial_learning_rate by ianstenbit in https://github.com/keras-team/keras-cv/pull/694
* Add script version to training history script by ianstenbit in https://github.com/keras-team/keras-cv/pull/688
* Add initial ResNet50V2 weights by ianstenbit in https://github.com/keras-team/keras-cv/pull/695
* Switch to SGD for basic_training by ianstenbit in https://github.com/keras-team/keras-cv/pull/698
* Introduce re-usable ObjectDetection components to KerasCV by LukeWood in https://github.com/keras-team/keras-cv/pull/686
* Removed bias from Conv2D if followed by BatchNorm. by sebastian-sz in https://github.com/keras-team/keras-cv/pull/697
* Add MobileNetV3 models by Rishit-dagli in https://github.com/keras-team/keras-cv/pull/526
* Introduce a PascalVOC loader as an API by LukeWood in https://github.com/keras-team/keras-cv/pull/703
* skip tests to try to prevent OOMs by LukeWood in https://github.com/keras-team/keras-cv/pull/708
* Add TFDS+Pandas as test deps for GPU tests by ianstenbit in https://github.com/keras-team/keras-cv/pull/709
* Add augmenter layer by ianstenbit in https://github.com/keras-team/keras-cv/pull/704
* Move loaders namespace to datasets for API consistency by LukeWood in https://github.com/keras-team/keras-cv/pull/711
* Add instructions for adding test deps by ianstenbit in https://github.com/keras-team/keras-cv/pull/714
* Encode labels in the tf.data pipeline for Object Detection models by LukeWood in https://github.com/keras-team/keras-cv/pull/705
* Add ragged bounding box support and utils to pad and filter ragged bounding boxes to keras cv by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/677
* Make ReduceLrOnPlateau a bit less patient for basic imagenet training by ianstenbit in https://github.com/keras-team/keras-cv/pull/723
* update demo scripts by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/722
* Update the API & train_step() of RetinaNet to encourage TPU compatible forward passes by LukeWood in https://github.com/keras-team/keras-cv/pull/721
* Add ConvNeXt by sayakpaul in https://github.com/keras-team/keras-cv/pull/678
* Restructure model tests to try to reduce OOM by ianstenbit in https://github.com/keras-team/keras-cv/pull/736
* Create ImageNet loader in keras_cv.datasets by ianstenbit in https://github.com/keras-team/keras-cv/pull/735
* Add improved ResNet50V2 weights by ianstenbit in https://github.com/keras-team/keras-cv/pull/741
* Support validation_data in `fit()` for KerasCV RetinaNet by LukeWood in https://github.com/keras-team/keras-cv/pull/743
* Add support for model kwargs to basic training script by ianstenbit in https://github.com/keras-team/keras-cv/pull/742
* Make loss reduction consistent with model garden by LukeWood in https://github.com/keras-team/keras-cv/pull/747
* Add support for segmentation mask in BaseImageAugmentationLayer by ianstenbit in https://github.com/keras-team/keras-cv/pull/748

New Contributors
* Rishit-dagli made their first contribution in https://github.com/keras-team/keras-cv/pull/526

**Full Changelog**: https://github.com/keras-team/keras-cv/compare/v0.2.10...v0.3.1

What's Changed
* Add a test case to enforce rescaling behavior by ianjjohnson in https://github.com/keras-team/keras-cv/pull/603
* Improves `serialization_test.py` to cover all argument with default values by atuleu in https://github.com/keras-team/keras-cv/pull/600
* Porting over ResNets from keras.applications by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/558
* Robust serialization test by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/591
* Add clip_to_image() util to bounding_box by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/607
* fix random_rotation bugs by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/608
* `classifier_activation` docstring corrections by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/610
* Fixed converters so that rel->rel don't require images by quantumalaviya in https://github.com/keras-team/keras-cv/pull/612
* Randomshear Bounding box augmentation Feature by pranavjadhav001 in https://github.com/keras-team/keras-cv/pull/373
* Style changes to NMS layer by LukeWood in https://github.com/keras-team/keras-cv/pull/613
* Added random_rotation_demo.py by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/555
* Add a link to the new COCO metric publication & keras.io docs by LukeWood in https://github.com/keras-team/keras-cv/pull/620
* Migrate iou_utils to the keras_cv.bounding_box namespace by quantumalaviya in https://github.com/keras-team/keras-cv/pull/598
* code style fixes in random_rotation.py by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/624
* Fixed error message when requirement does not meet for minimum TF version by adhadse in https://github.com/keras-team/keras-cv/pull/563
* Add an initial Densenet/Imagenet classification training script by ianjjohnson in https://github.com/keras-team/keras-cv/pull/618
* Fix NMSLayer shape inference to work when no elements are present by LukeWood in https://github.com/keras-team/keras-cv/pull/631
* Fixed reference sections in some docstrings by quantumalaviya in https://github.com/keras-team/keras-cv/pull/633
* Add pre-trained weight loading (starting with DenseNet121) by ianjjohnson in https://github.com/keras-team/keras-cv/pull/627
* Update basic_training example to only save the best weights by ianjjohnson in https://github.com/keras-team/keras-cv/pull/635
* Add initial weight exporting scripts by ianjjohnson in https://github.com/keras-team/keras-cv/pull/628
* Adding new NMS tests by quantumalaviya in https://github.com/keras-team/keras-cv/pull/642
* Add input-tensor param to all KerasCV.models by ianjjohnson in https://github.com/keras-team/keras-cv/pull/639
* Use fstring format in models/weights.py by ianjjohnson in https://github.com/keras-team/keras-cv/pull/645
* Silence E402 linter error by ianjjohnson in https://github.com/keras-team/keras-cv/pull/651
* added RandomFlip to Keras_CV by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/562
* Switch to tensorboard.dev for training metadata handling by ianjjohnson in https://github.com/keras-team/keras-cv/pull/648
* Add Focal Loss by quantumalaviya in https://github.com/keras-team/keras-cv/pull/615
* Cleanup and polish on basic_training.py by ianjjohnson in https://github.com/keras-team/keras-cv/pull/652
* Rename num_classes to classes across entire repo by ianjjohnson in https://github.com/keras-team/keras-cv/pull/657

New Contributors
* adhadse made their first contribution in https://github.com/keras-team/keras-cv/pull/563

**Full Changelog**: https://github.com/keras-team/keras-cv/compare/v0.2.9...v0.2.10

What's Changed
* Added parameterized tests to RRC by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/550
* Add seeds for random distribution sampling by quantumalaviya in https://github.com/keras-team/keras-cv/pull/557
* Add support for unbatch bounding boxes to convert_format() by LukeWood in https://github.com/keras-team/keras-cv/pull/556
* Squeeze and Excite block by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/505
* Fixed 425 with Lambda layer by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/559
* Add default name to DenseNet (to match docstring) by ianjjohnson in https://github.com/keras-team/keras-cv/pull/574
* [Devcontainer] Fix isort extension name by bhack in https://github.com/keras-team/keras-cv/pull/569
* Added visualization feature to demo utils by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/567
* Adding Non-Max Suppression Layer by quantumalaviya in https://github.com/keras-team/keras-cv/pull/564
* Migrate VGG19 to keras_cv.models by ianjjohnson in https://github.com/keras-team/keras-cv/pull/573
* Adds support for ragged tensor to bounding_box.convert_format by atuleu in https://github.com/keras-team/keras-cv/pull/572
* Update NMS Layer file location by LukeWood in https://github.com/keras-team/keras-cv/pull/576
* Minor edits to make bounding box utilities more idiomatic by LukeWood in https://github.com/keras-team/keras-cv/pull/577
* Add serialization test for NMS by quantumalaviya in https://github.com/keras-team/keras-cv/pull/578
* Changed BaseImageAugmentationLayer to preserve additional unmodified … by sebastian-sz in https://github.com/keras-team/keras-cv/pull/568
* Add MLP Mixer models by sayakpaul in https://github.com/keras-team/keras-cv/pull/529
* Towards keypoint support: `BaseImageAugmentationLayer` modification by atuleu in https://github.com/keras-team/keras-cv/pull/586
* Add CSPDarkNet, DarkNet21 & DarkNet53 by quantumalaviya in https://github.com/keras-team/keras-cv/pull/541
* Towards keypoint support: Converter and utility functions by atuleu in https://github.com/keras-team/keras-cv/pull/585
* Include with_targets to RandomResizedCrop by LukeWood in https://github.com/keras-team/keras-cv/pull/597

New Contributors
* atuleu made their first contribution in https://github.com/keras-team/keras-cv/pull/572

**Full Changelog**: https://github.com/keras-team/keras-cv/compare/v0.2.8...v0.2.9

What's Changed
* Roadmap by LukeWood in https://github.com/keras-team/keras-cv/pull/498
* Stochastic Depth argument name correction by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/497
* Correction in `layers.__init__.py` by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/503
* Migrate RandomRotation to Keras_CV by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/493
* random jpeg quality by artu1999 in https://github.com/keras-team/keras-cv/pull/437
* added yxyx and rel_yxyx bounding box format support in bounding box utils by divyashreepathihalli in https://github.com/keras-team/keras-cv/pull/510
* Remove "tf.keras.__internal__.layers" from all files by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/516
* Drop Path by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/480
* add: PR description template. by sayakpaul in https://github.com/keras-team/keras-cv/pull/525
* Add an augment_label method to the RandomGaussianBlur augmentation layer by ianjjohnson in https://github.com/keras-team/keras-cv/pull/537
* Update all preprocessing layer demos to use demo_utils by ianjjohnson in https://github.com/keras-team/keras-cv/pull/535
* Remove references to data_format by ricardoprins in https://github.com/keras-team/keras-cv/pull/531
* Fix DenseNet Docstring by quantumalaviya in https://github.com/keras-team/keras-cv/pull/539
* Change all __call__ arguments using tf.float32 as a default to the string "float32" by ricardoprins in https://github.com/keras-team/keras-cv/pull/542
* Update serialization_test.py by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/544
* Random Resized Crop by AdityaKane2001 in https://github.com/keras-team/keras-cv/pull/499

New Contributors
* ianjjohnson made their first contribution in https://github.com/keras-team/keras-cv/pull/537
* ricardoprins made their first contribution in https://github.com/keras-team/keras-cv/pull/531

**Full Changelog**: https://github.com/keras-team/keras-cv/compare/v0.2.7...v0.2.8