0.7.2.dev1

What's Changed

• CherryPick - Align config with Keras NLP (#2217) by @sampathweb in #2218

Full Changelog: 0.7.2.dev0...0.7.2.dev1

0.7.2.dev0

What's Changed

• r0.7.2 Cherry Pick by @sampathweb in #2215

Full Changelog: v0.7.1...0.7.2.dev0

0.7.1

Summary

KerasCV is now compatible with Keras 3 (TensorFlow, Jax and PyTorch backends). Users utilizing tf-nightly or Keras 3.0 can expect seamless compatibility with KerasCV. KerasCV also works with Keras 2.0 (with TensorFlow).

What's Changed

• Update the comment of the num_classes parameter of deeplab v3 by @aaudevart in #2071
• Set read-only tokens for all GitHub workflows by @pnacht in #2075
• Add the Segment Anything Model to KerasCV by @tirthasheshpatel in #1987
• Export SD submodels by @jbischof in #2080
• adding deeplab_v3_plus_presets by @divyashreepathihalli in #2051
• [Yolov8 detector] Fix example in docstring by @cosmo3769 in #2082
• Bump python version requirement to 3.9 by @mattdangerw in #2079
• [SAM] Fixed shape issue in example in docstring by @cosmo3769 in #2083
• Use "masks" and "boxes" as prompt keys for SAM by @ianstenbit in #2084
• Support partial prompting in SAM by @ianstenbit in #2085
• Explicitly specify full package for more modules, as shown in #2001 by @BjarneHerland in #2077
• Update VITDet to conform to KerasCV scaling standards by @ianstenbit in #2086
• Resolve mean/std swap for VITDet backbone by @ianstenbit in #2087
• Support importing Keras3 as Keras instead of Keras Core by @ianstenbit in #2089
• remove tests from pypi build by @haifeng-jin in #2094
• Export task models as both models.task.Model and models.Model by @ianstenbit in #2093
• Fix CSPDarkNetBackbone export by @ianstenbit in #2096
• Fix PyTorch tests by @ianstenbit in #2097
• Doc updates to switch branding to Keras 3 by @ianstenbit in #2092
• Fix a flaky test for Segment Anything by @ianstenbit in #2090
• Fix decoding of LabelEncoder for RetinaNet by @ianstenbit in #2099
• Use the proper title for example by @Philmod in #2109
• Fixes Fine-tuning Stable Diffusion by @ID6109 in #2113
• Fixed typo in README.md by @AniketP04 in #2106
• Update mask_invalid_detections.py by @VBPMP in #2117
• Fix the issue (#2102): Add cast to float32 from float16 into Stable D… in #2124
• Fix RetinaNet shape issue by @tirthasheshpatel in #2119
• update reviewers names by @divyashreepathihalli in #2130
• update keras-cv json file name by @divyashreepathihalli in #2128
• Improve keras 3 detection by @divyashreepathihalli in #2132
• Fix Segment Anything Model saving bug by @tirthasheshpatel in #2138
• Adds Nightly package for keras-cv by @sampathweb in #2139
• Set a security policy by @pnacht in #2142
• add Random ops shim by @divyashreepathihalli in #2145
• Replace RandomGenerator with SeedGenerator by @sampathweb in #2150
• Revert "Replace RandomGenerator with SeedGenerator" by @sampathweb in #2161
• Keras 3 compatibility by @divyashreepathihalli in #2170
• fix noise scheduler error in stable diffusion by @divyashreepathihalli in #2171
• Fix the issue(#2158): Add some file names into .gitignore by @y-vectorfield in #2159
• fix shapes error if images was a list. by @divyashreepathihalli in #2173
• Removed setup.py develop from documentation, replaced with pip instal… by @EdIzaguirre in #2118
• Remove keras-nightly pin by @sampathweb in #2174
• fix model None error by @divyashreepathihalli in #2176
• update version error by @divyashreepathihalli in #2175
• Fixes Saving Format related test failures for Keras 3 by @sampathweb in #2180
• Version bump to 0.7.1.dev0 by @sampathweb in #2183
• convert to tensor before smart resize (#2184) by @sampathweb in #2185
• version bump to 0.7.1 by @sampathweb in #2186

New Contributors

• @aaudevart made their first contribution in #2071
• @pnacht made their first contribution in #2075
• @mattdangerw made their first contribution in #2079
• @BjarneHerland made their first contribution in #2077
• @Philmod made their first contribution in #2109
• @AniketP04 made their first contribution in #2106
• @VBPMP made their first contribution in #2117
• @y-vectorfield made their first contribution in #2159
• @EdIzaguirre made their first contribution in #2118

Full Changelog: v0.6.4...v0.7.1

0.7.1.dev0

What's Changed

• Update the comment of the num_classes parameter of deeplab v3 by @aaudevart in #2071
• Set read-only tokens for all GitHub workflows by @pnacht in #2075
• Add the Segment Anything Model to KerasCV by @tirthasheshpatel in #1987
• Export SD submodels by @jbischof in #2080
• adding deeplab_v3_plus_presets by @divyashreepathihalli in #2051
• [Yolov8 detector] Fix example in docstring by @cosmo3769 in #2082
• Bump python version requirement to 3.9 by @mattdangerw in #2079
• [SAM] Fixed shape issue in example in docstring by @cosmo3769 in #2083
• Use "masks" and "boxes" as prompt keys for SAM by @ianstenbit in #2084
• Support partial prompting in SAM by @ianstenbit in #2085
• Explicitly specify full package for more modules, as shown in #2001 by @BjarneHerland in #2077
• Update VITDet to conform to KerasCV scaling standards by @ianstenbit in #2086
• Resolve mean/std swap for VITDet backbone by @ianstenbit in #2087
• Support importing Keras3 as Keras instead of Keras Core by @ianstenbit in #2089
• remove tests from pypi build by @haifeng-jin in #2094
• Export task models as both models.task.Model and models.Model by @ianstenbit in #2093
• Fix CSPDarkNetBackbone export by @ianstenbit in #2096
• Fix PyTorch tests by @ianstenbit in #2097
• Doc updates to switch branding to Keras 3 by @ianstenbit in #2092
• Fix a flaky test for Segment Anything by @ianstenbit in #2090
• Fix decoding of LabelEncoder for RetinaNet by @ianstenbit in #2099
• Use the proper title for example by @Philmod in #2109
• Fixes Fine-tuning Stable Diffusion by @ID6109 in #2113
• Fixed typo in README.md by @AniketP04 in #2106
• Update mask_invalid_detections.py by @VBPMP in #2117
• Fix the issue (#2102): Add cast to float32 from float16 into Stable D… in #2124
• Fix RetinaNet shape issue by @tirthasheshpatel in #2119
• update reviewers names by @divyashreepathihalli in #2130
• update keras-cv json file name by @divyashreepathihalli in #2128
• Improve keras 3 detection by @divyashreepathihalli in #2132
• Fix Segment Anything Model saving bug by @tirthasheshpatel in #2138
• Adds Nightly package for keras-cv by @sampathweb in #2139
• Set a security policy by @pnacht in #2142
• add Random ops shim by @divyashreepathihalli in #2145
• Replace RandomGenerator with SeedGenerator by @sampathweb in #2150
• Revert "Replace RandomGenerator with SeedGenerator" by @sampathweb in #2161
• Keras 3 compatibility by @divyashreepathihalli in #2170
• fix noise scheduler error in stable diffusion by @divyashreepathihalli in #2171
• Fix the issue(#2158): Add some file names into .gitignore by @y-vectorfield in #2159
• fix shapes error if images was a list. by @divyashreepathihalli in #2173
• Removed setup.py develop from documentation, replaced with pip instal… by @EdIzaguirre in #2118
• Remove keras-nightly pin by @sampathweb in #2174
• fix model None error by @divyashreepathihalli in #2176
• update version error by @divyashreepathihalli in #2175
• Fixes Saving Format related test failures for Keras 3 by @sampathweb in #2180
• Version bump to 0.7.1.dev0 by @sampathweb in #2183

New Contributors

• @aaudevart made their first contribution in #2071
• @pnacht made their first contribution in #2075
• @mattdangerw made their first contribution in #2079
• @BjarneHerland made their first contribution in #2077
• @Philmod made their first contribution in #2109
• @AniketP04 made their first contribution in #2106
• @VBPMP made their first contribution in #2117
• @y-vectorfield made their first contribution in #2159
• @EdIzaguirre made their first contribution in #2118

Full Changelog: v0.6.4...0.7.1.dev0

v0.7.0.dev0

Summary

• KerasCV is now compatible with Keras 3. Users utilizing tf-nightly or Keras 3.0 can expect seamless compatibility with KerasCV.
• bug fixes

What's Changed

• Update the comment of the num_classes parameter of deeplab v3 by @aaudevart in #2071
• Set read-only tokens for all GitHub workflows by @pnacht in #2075
• Add the Segment Anything Model to KerasCV by @tirthasheshpatel in #1987
• Export SD submodels by @jbischof in #2080
• adding deeplab_v3_plus_presets by @divyashreepathihalli in #2051
• [Yolov8 detector] Fix example in docstring by @cosmo3769 in #2082
• Bump python version requirement to 3.9 by @mattdangerw in #2079
• [SAM] Fixed shape issue in example in docstring by @cosmo3769 in #2083
• Use "masks" and "boxes" as prompt keys for SAM by @ianstenbit in #2084
• Support partial prompting in SAM by @ianstenbit in #2085
• Explicitly specify full package for more modules, as shown in #2001 by @BjarneHerland in #2077
• Update VITDet to conform to KerasCV scaling standards by @ianstenbit in #2086
• Resolve mean/std swap for VITDet backbone by @ianstenbit in #2087
• Support importing Keras3 as Keras instead of Keras Core by @ianstenbit in #2089
• remove tests from pypi build by @haifeng-jin in #2094
• Export task models as both models.task.Model and models.Model by @ianstenbit in #2093
• Fix CSPDarkNetBackbone export by @ianstenbit in #2096
• Fix PyTorch tests by @ianstenbit in #2097
• Doc updates to switch branding to Keras 3 by @ianstenbit in #2092
• Fix a flaky test for Segment Anything by @ianstenbit in #2090
• Fix decoding of LabelEncoder for RetinaNet by @ianstenbit in #2099
• Use the proper title for example by @Philmod in #2109
• Fixes Fine-tuning Stable Diffusion by @ID6109 in #2113
• Fixed typo in README.md by @AniketP04 in #2106
• Update mask_invalid_detections.py by @VBPMP in #2117
• Fix the issue (#2102): Add cast to float32 from float16 into Stable D… in #2124
• Fix RetinaNet shape issue by @tirthasheshpatel in #2119
• update reviewers names by @divyashreepathihalli in #2130
• update keras-cv json file name by @divyashreepathihalli in #2128
• Improve keras 3 detection by @divyashreepathihalli in #2132
• Fix Segment Anything Model saving bug by @tirthasheshpatel in #2138
• Adds Nightly package for keras-cv by @sampathweb in #2139
• Set a security policy by @pnacht in #2142
• add Random ops shim by @divyashreepathihalli in #2145
• Replace RandomGenerator with SeedGenerator by @sampathweb in #2150
• Revert "Replace RandomGenerator with SeedGenerator" by @sampathweb in #2161
• Keras 3 compatibility by @divyashreepathihalli in #2170
• fix noise scheduler error in stable diffusion by @divyashreepathihalli in #2171
• Version bump to 0.7.0.dev0 by @divyashreepathihalli in #2172

New Contributors

• @aaudevart made their first contribution in #2071
• @pnacht made their first contribution in #2075
• @mattdangerw made their first contribution in #2079
• @BjarneHerland made their first contribution in #2077
• @Philmod made their first contribution in #2109
• @AniketP04 made their first contribution in #2106
• @VBPMP made their first contribution in #2117

Full Changelog: v0.6.4...v0.7.0.dev0

v0.6.4

Fix an import issue from 0.6.2 and 0.6.3

What's Changed

• Fix input path for visualization issue by @ianstenbit in #2068
• Update version to 0.6.4 by @ianstenbit in #2069

Full Changelog: v0.6.3...v0.6.4

v0.6.3

This is a minor bug fix to resolve some import issues with 0.6.2

What's Changed

• Fix some imports in KerasCV that are invalid with Namex by @ianstenbit in #2064
• Update version to 0.6.3 by @ianstenbit in #2066

Full Changelog: v0.6.2...v0.6.3

v0.6.2

With this release, we're bringing Stable Diffusion to multi-backend Keras, as well as a few other improvements

Introduction of SegFormer for semantic segmentation
Improvements to DeepLabV3Plus
Expansion of segmentation mask support in preprocessing layers
Migrating CenterPillar (3D OD) to multi-backend Keras
Thank you to all of our wonderful contributors for your efforts on this release!

What's Changed

• Update README for Keras Core by @jbischof in #1936
• Remove unneeded environment variable by @jbischof in #1938
• Fix markdown formatting by @jbischof in #1937
• Port DeepLabV3 segmentation model from keras_cv.models.legacy to the Task API by @soumik12345 in #1831
• Add GPU testing for Jax+Torch by @ianstenbit in #1935
• Update quickstart for Keras Core by @jbischof in #1945
• Add Keras Core as an install dep by @ianstenbit in #1949
• Fix MBConv Layer for Quickstart by @ianstenbit in #1951
• Support segmentation mask in cutmix preprocessing layer by @cosmo3769 in #1892
• Port DeepLabV3+ to Keras Core by @ianstenbit in #1943
• Readme patch by @DavidLandup0 in #1955
• Replacing tf with np in some files by @ID6109 in #1956
• Add segmentation mask support to Mosaic and JitteredResize by @ianstenbit in #1958
• Use p5 output instead of p4 for deeplab high-level features by @ianstenbit in #1961
• U-Net Research Paper Attached, Linter Issue Solved by @NiharJani2002 in #1959
• Replacing tf with np in some more files by @ID6109 in #1962
• Fit predict by @Xrenya in #1963
• Fix linter error (bad PR merged in #1959 which broke linter) by @ianstenbit in #1966
• Refactor CSPDarknet for readability by @cosmo3769 in #1921
• Migrate CenterPillar to the Backbone+Task API by @ianstenbit in #1953
• Update ImageNet training script to support Keras Core by @ianstenbit in #1976
• Waymo Dataset's Research Paper And Website Link Attached In load.py o… by @NiharJani2002 in #1975
• Fix broken StableDiffusion tests by @ianstenbit in #1980
• Add Augmenter utility by @jbischof in #1978
• Remove pinning of keras-core, set min TF vers to 2.13 by @sampathweb in #1983
• A README for the preprocessing layers by @ariG23498 in #1979
• Add support of segmentation mask to fourier mix by @cosmo3769 in #1991
• Testing bounding boxes in WithMixedPrecisionTest by @jaygala223 in #1860
• RandomGaussianBlur crashes when factor=0 by @muxamilian in #1968
• Fix lint issue with Waymo data loader by @ianstenbit in #1993
• Add support of segmentation mask in Augmix layer by @cosmo3769 in #1988
• Use Namex for API generation by @ianstenbit in #1995
• Fix Keras serialization naming collision by @ianstenbit in #2001
• Add bug template by @jbischof in #2016
• [RandomTranslation] Supporting Segmentation Masks by @IMvision12 in #2024
• Restructure retinanet steps to avoid modifying args by @ianstenbit in #2029
• Use non-ragged outputs in MultiClassNMS by @ianstenbit in #2030
• Use correct convention for static shape in point_cloud grouping by @ianstenbit in #2028
• Migrate Efficientnetlite to Backbone by @cosmo3769 in #1877
• Migrate Efficientnetv1 to Backbone by @cosmo3769 in #1716
• Issue_1957 Returning the Matplotlib plt object in the plot_bounding_box_gallery.py file by @Zekrom-7780 in #2000
• [EfficientNetV2 Backbone] Style fix by @cosmo3769 in #2031
• Add pre-trained MobileNetV3Small preset by @ianstenbit in #2034
• [MobileNetV3Backbone] alias fix + doc fix in preset by @cosmo3769 in #2035
• keras.layers.add->keras.layers.Add by @cosmo3769 in #2033
• Added support of segmentation mask in RandomShear Layer by @cosmo3769 in #2021
• [RandomZoom] Supporting Segmentation Masks by @ariG23498 in #2010
• Add support of segmentation mask in RandomCutout by @cosmo3769 in #2004
• Remove forward slashes from layer names for backbones by @ianstenbit in #2037
• [DeepVision Port] SegFormer and Mix-Transformers by @DavidLandup0 in #1946
• Fix test errors that were introduced by upgrading to Keras Core 0.1.5 by @ianstenbit in #2041
• Port CenterPillar to Keras Core by @ianstenbit in #2003
• Fix code example in RetinaNet class docstring by @DiegoMont in #2045
• Re-write YOLOV8LabelEncoder from scratch by @ianstenbit in #2044
• Migrate StableDiffusion to Keras Core by @jbischof in #1982
• Update centernet_label_encoder.py by @qlzh727 in #2052
• Default to jit_compile=True for SD by @ianstenbit in #2054
• Update version to 0.6.2 by @ianstenbit in #2053
• Add the full Waymo 3D object detection example by @ianstenbit in #1977
• Fix loss computation for CenterPillar when batch_size > 1 by @ianstenbit in #2056
• Remove direct imports of tf.keras by @ianstenbit in #2048
• Add namex to release action by @ianstenbit in #2058
• Add keras-core as a dependency for release by @ianstenbit in #2059
• Install all deps for release cut. by @ianstenbit in #2060
• Re-include non-dependencies required for release by @ianstenbit in #2062

New Contributors

• @soumik12345 made their first contribution in #1831
• @NiharJani2002 made their first contribution in #1959
• @Xrenya made their first contribution in #1963
• @sampathweb made their first contribution in #1983
• @muxamilian made their first contribution in #1968
• @Zekrom-7780 made their first contribution in #2000
• @DiegoMont made their first contribution in #2045

Full Changelog: v0.6.1...v0.6.2

v0.6.1

This is a fast-follow to 0.6.0 with two notable fixes:

• Re-added support for TF 2.12
• Fixed Non-Max-Suppression for Keras Core + TensorFlow backend

What's Changed

• Fix Devcontainer by @ianstenbit in #1930
• Use TF-native NMS when in TF backend by @ianstenbit in #1931
• Switch back to tf 2.12 as minimum version by @ianstenbit in #1934

Full Changelog: v0.6.0...v0.6.1

v0.6.0

KerasCV is adding experimental support for Jax and PyTorch backends on top of the Keras Core library. Read the anouncement, and browse the full library documentation, including how to specify the backend when running your code.

Support for both Jax and PyTorch is still experimental, expect some rough edges and please give us feedback!

Summary

This release should be equivalent to 0.5.1 with the addition of multi-backend support.
The following API components do not yet support Jax + PyTorch:

• keras_cv.models.StableDiffusion[V2]
• keras_cv.models.MultiHeadCenterPillar
• keras_cv.training.ContrastiveTrainer
• All models under keras_cv.models.legacy

Note that there are two ways you can run on top of Tensorflow.
If you run your scripts/colab without any changes, KerasCV will use tf.keras for all layer and modeling implementations. This should be a no-op from previous releases of the library.

If you run your scripts/colab with KERAS_BACKEND={jax, torch, tensorflow}, you will be trying the new Keras Core library, using the specified backend. This is a great way to test out the future of the library!

Full details on runtime specification is available along with the Keras Core documentation.

What's Changed

• Add support for PyTorch and Jax to KerasCV by @tirthasheshpatel in #1925
• Update version to dev release by @ianstenbit in #1927

New Contributors

• @tirthasheshpatel made their first contribution in #1925

Full Changelog: v0.5.1...v0.6.0.dev0