v0.3.5

What's Changed

• Update unit test and golden numbers in KPL by @qlzh727 in #864
• Support no image size in PascalVOC loader by @LukeWood in #862
• Make separate benchmark methods for single and multi-gpu benchmarks by @ianstenbit in #867
• revert keypoint refactoring. by @tanzhenyu in #869
• Add deeplab_v3 model with keras cv components only by @qlzh727 in #856
• Update the instructions to update the cloudbuild cluster by @LukeWood in #832
• Address review comments from #874 by @qlzh727 in #875
• Support mixed-precision training in basic_training script by @ianstenbit in #878
• Add FasterRCNN model. by @tanzhenyu in #870
• Fix the unit test for segmentation head serialization. by @qlzh727 in #882
• Add Atrous Spatial Pyramid Pooling as a feature decoder layer by @qlzh727 in #884
• Add contributing docs about new model weights by @ianstenbit in #889
• Add devcontainer CI by @bhack in #893
• Improve FasterRCNN model quality. by @tanzhenyu in #898
• Minor performance improvements to basic ImageNet training by @ianstenbit in #902
• Add pre-trained weights for EfficientNetV2B0 by @ianstenbit in #906
• Filter pull request directory by @bhack in #899
• Make RandomFlip perform horizontal flipping only by default by @ianstenbit in #903
• Add distributed training, and further improve training quality. by @tanzhenyu in #914
• Add some pre-trained weight info to README by @ianstenbit in #913
• Adds the VAEEncoder to StableDiffusion by @LukeWood in #873
• Allow compute_iou to take boxes of different shape. by @tanzhenyu in #919
• Add pretrained EfficientNetV2b1 weights by @ianstenbit in #923
• update readme and roadmap. by @tanzhenyu in #934
• Fix typo in name of devcontainer workflow by @ianstenbit in #940
• Add model fit for FasterRCNN. by @tanzhenyu in #925
• Update MobileNet docs to point to the correct paper by @ianstenbit in #948
• Add pascal voc 2012 dataset with segmentation data. by @qlzh727 in #943
• Add RandomCropAndResize to ImageNet classification training script by @ianstenbit in #935
• Add better weights for ResNet50V2 by @ianstenbit in #952
• Fixed efficientnet v1 correct pad. by @sebastian-sz in #927
• Update the RetinaNet example by @LukeWood in #942
• Add tf.function(jit_compile=True) for the PNG decode function. by @qlzh727 in #953
• Add IoU3D as a custom c++ op (CPU) by @ianstenbit in #890
• bug fix in image_encoder.py by @LukeWood in #955
• Pre-trained weights for EfficientNetV2B2 by @ianstenbit in #956
• Training script improvement proposal by @DavidLandup0 in #908
• Devcontainer GPU support #945 by @jacoverster in #946
• Fix build target for custom ops by @ianstenbit in #959
• Step 1/3. add dummy semantic segmentation training script. by @tanzhenyu in #957
• Step 2/3: add Sbd data by @tanzhenyu in #961
• Fix casting issue with basic training learning rate schedule by @ianstenbit in #965
• Add waymo dataset loader by @ianstenbit in #966
• Add weights for EfficientNetV2S by @ianstenbit in #971
• citing reference. by @tanzhenyu in #972
• Fix reproducability issue of seeded StableDiffusion runs by @ianstenbit in #962
• Added mixed_precision support for preprocessing layers. by @sebastian-sz in #967
• Save best weights only for basic_training by @ianstenbit in #977
• 630/add efficientnet lite by @sebastian-sz in #921
• Shuffle dataset every epoch for basic_training by @ianstenbit in #983
• Track encoded boxes in the RetinaNet in a Keras metric by @LukeWood in #964
• Step 3/3: Update DeeplabV3 model by @tanzhenyu in #975
• Add README about Waymo Open Dataset dependency by @ianstenbit in #985
• Lazy-load components of StableDiffusion and make them visible to users by @ianstenbit in #989
• Add text-conditioned in-painting functionality to Keras Stable Diffusion by @bobqywei in #973
• Add support for add_tokens() to StableDiffusion in order to support TextualInversion by @LukeWood in #831
• Add bounding box support to resizing by @LukeWood in #861
• Implement bounding boxes for RandomCropAndResize by @AmedeoBiolatti in #994
• Update README.md with disclaimer by @LukeWood in #993
• Avoid retracing with python lazy_loading by @bhack in #997
• Restructure StableDiffusion namespace and folder hierarchy by @ianstenbit in #1002
• fix serializationt test. by @tanzhenyu in #1004
• SimCLR Training Script by @ianstenbit in #717
• Add seed=seed, param_name to factor parsing for layers.Mosaic() by @LukeWood in #881
• Adding ViT Components/Layers by @DavidLandup0 in #929
• Add base augmentation layer for 3D preception. by @lengzq in #986
• [Object Detection] Update retinanet predict loop to enable TPU support by @ianstenbit in #1017
• [Object Detection] Introduce a callback-based coco metric evaluator by @ianstenbit in #1000
• fixed transformer encoder dims per head by @DavidLandup0 in #1013
• Revert "[Object Detection] Update retinanet predict loop to enable TPU support" by @ianstenbit in #1022
• ResNet and ResNetV2 - Typo fix in docstrings by @DavidLandup0 in #1023
• Adding RegNets to keras_cv by @AdityaKane2001 in #739
• Add global_z_rotation data augmentation and wrap_angle_rad helper function. by @lengzq in #1012
• [Backbones] Add pre-trained weights for DarkNet53 by @ianstenbit in #1029
• [Object Detection] RetinaNet: custom predict_function by @ianstenbit in #1021
• [Object Detection] Speed up the PyCOCO callback by only calling model.predict once by @ianstenbit in #1026
• Add mixed precision for deeplab. by @tanzhenyu in #1032
• Update group_normalization.py by @charbull in #1035
• [Backbone Training] added 50/50 between cutmix and mixup, changed default hold steps by @DavidLandup0 in #980
• IoULoss documentation typo fix by @DavidLandup0 in #1038
• Add four global data augmentations for 3D by @lengzq in #1028
• Add pre-trained weights for CSPDarkNet by @ianstenbit in #1036
• [Draft] Polish the RetinaNet by @LukeWood in #984
• fix for dynamic shape. by @tanzhenyu in #1042
• fix fasterrcnn train dataset. by @tanzhenyu in #1046
• [Stable Diffusion] Noise scheduler for fine-tuning and textual inversion by @ianstenbit in #1045
• polish roadmap and readme. by @tanzhenyu in #1009
• Introduced a new internal util to preserve relative format by @quantumalaviya in #1016
• Add group_points_by_bounding_boxes data augmentation. by @lengzq in #1040
• [Semantic Segmentation] Add first segmentation weights (credit @tanzhenyu) by @ianstenbit in #1059
• (Ragged OD Pipeline Step 1/3) Support RaggedImages and Bounding Boxes in BaseImageAugmentationLayer by @LukeWood in #1047
• [Object Detection] Remove train_time_metrics from RetinaNet by @ianstenbit in #1041
• [3D Object Detection] Make iou_3d a function by @ianstenbit in #1060
• Step 1/4 [ObjectDetection]: allow PyCOCOCallback to take apply_nms by @tanzhenyu in #1061
• Implement bounding boxes for random choice by @AmedeoBiolatti in #998
• Revert "Implement bounding boxes for random choice" by @ianstenbit in #1065
• (Step 2/3) creates a JitteredResize layer by @LukeWood in #1053
• Update stable_diffusion num_steps to be 50 by @LukeWood in #1067
• fix several failing test / scripts due to recent PR merge. by @tanzhenyu in #1069
• Introducing randomly pasting objects data augmentation. by @lengzq in #1058
• Re-introduce evaluate_train_step_metrics API by @LukeWood in #1071
• Switch to one-configuration-per-architecture GCB testing for backbones by @ianstenbit in #1070
• move fasterrcnn to a new path. by @tanzhenyu in #1072
• Fix patch that somehow got dropped by @LukeWood in #1076
• Add data transformer for Waymo Open Dataset by @Guowang in #1066
• Introduce swap background data augmentation. by @lengzq in #1078
• 3D data augmentation cleanup by @lengzq in #1082
• [3D Object Detection] Waymo dataloading + augmentation flow example by @ianstenbit in #1083
• Customized op for WithinBox3d. by @tanzhenyu in #1020
• Introduce random drop box 3D data augmentation. by @lengzq in #1084
• Add a note about mixed precision to SD inpaint by @ianstenbit in #1088
• replace is_within_box3d with is_within_any_box3d. by @tanzhenyu in #1087
• Group points by boxes v2 by @tanzhenyu in #1090
• [3D Object Detection] Add initial 3D box format by @ianstenbit in #1064
• Fix ragged_tensor resize new case by @bhack in #891
• Fix broken build by @ianstenbit in #1093
• Introduce frustum based drop points by @lengzq in #1091
• Fix typos in tests and add 3d augmentations to init. by @lengzq in #1096
• Gate RandomCopyPasteTest on TEST_CUSTOM_OPS flag by @ianstenbit in #1097
• [Mixed Precision Support] MixUp Layer by @DavidLandup0 in #1092
• Fixed a Minor Typo by @aflah02 in #1094
• Fix RetinaNet training on TPU. by @tanzhenyu in #1113
• Prefix custom op names with kcv by @ianstenbit in #1115
• Introduce frustum-based point feature noise. by @lengzq in #1098
• Delete .so files by @ianstenbit in #1116
• transform records. by @tanzhenyu in #1089
• (OD input pipeline Step 3/4) Add RandomAspectRatio layer by @LukeWood in #1054

New Contributors

• @DavidLandup0 made their first contribution in #908
• @jacoverster made their first contribution in #946
• @bobqywei made their first contribution in #973
• @AmedeoBiolatti made their first contribution in #994
• @lengzq made their first contribution in #986
• @charbull made their first contribution in #1035
• @Guowang made their first contribution in #1066
• @aflah02 made their first contribution in #1094

Full Changelog: v0.3.4...v0.3.5