Skip to content

Releases: keras-team/keras

Keras 3.12.0

27 Oct 20:22
@fchollet fchollet
v3.12.0
adbfd13
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Keras 3.12.0 Latest
Latest

Highlights

Keras has a new model distillation API!

You now have access to an easy-to-use API for distilling large models into small models while minimizing performance drop on a reference dataset -- compatible with all existing Keras models. You can specify a range of different distillation losses, or create your own losses. The API supports multiple concurrent distillation losses at the same time.

Example:

# Load a model to distill
teacher = ...
# This is the model we want to distill it into
student = ...

# Configure the process
distiller = Distiller(
    teacher=teacher,
    student=student,
    distillation_losses=LogitsDistillation(temperature=3.0),
)
distiller.compile(
    optimizer='adam',
    loss='sparse_categorical_crossentropy',
    metrics=['accuracy']
)

# Train the distilled model
distiller.fit(x_train, y_train, epochs=10)

Keras supports GPTQ quantization!

GPTQ is now built into the Keras API. GPTQ is a post-training, weights-only quantization method that compresses a model to int4 layer by layer. For each layer, it uses a second-order method to update weights while minimizing the error on a calibration dataset.

Learn how to use it in this guide.

Example:

model = keras_hub.models.Gemma3CausalLM.from_preset("gemma3_1b")
gptq_config = keras.quantizers.GPTQConfig(
    dataset=calibration_dataset,
    tokenizer=model.preprocessor.tokenizer,
    weight_bits=4,
    group_size=128,
    num_samples=256,
    sequence_length=256,
    hessian_damping=0.01,
    symmetric=False,
    activation_order=False,
)
model.quantize("gptq", config=gptq_config)
outputs = model.generate(prompt, max_length=30)

Better support for Grain datasets!

  • Add Grain support to keras.utils.image_dataset_from_directory and keras.utils.text_dataset_from_directory. Specify format="grain" to return a Grain dataset instead of a TF dataset.
  • Make almost all Keras preprocessing layers compatible with Grain datasets.

New features

  • Add keras.layers.ReversibleEmbedding layer: an embedding layer that can also also project backwards to the input space. Use it with the reverse argument in call().
  • Add argument opset_version in model.export(). Argument specific to format="onnx"; specifies the ONNX opset version.
  • Add keras.ops.isin op.
  • Add keras.ops.isneginf, keras.ops.isposinf ops.
  • Add keras.ops.isreal op.
  • Add keras.ops.cholesky_inverse op and add upper argument in keras.ops.cholesky.
  • Add keras.ops.image.scale_and_translate op.
  • Add keras.ops.hypot op.
  • Add keras.ops.gcd op.
  • Add keras.ops.kron op.
  • Add keras.ops.logaddexp2 op.
  • Add keras.ops.view op.
  • Add keras.ops.unfold op.
  • Add keras.ops.jvp op.
  • Add keras.ops.trapezoid op.
  • Add support for over 20 news ops with the OpenVINO backend.

Breaking changes

  • Layers StringLookup & IntegerLookup now save vocabulary loaded from file. Previously, when instantiating these layers from a vocabulary filepath, only the filepath would be saved when saving the layer. Now, the entire vocabulary is materialized and saved as part of the .keras archive.

Security fixes

New Contributors

Full Changelog: v3.11.0...v3.12.0

Contributors

WIgor, SamKnightGit, and 14 other contributors
Assets 2
Loading

Keras 3.11.3

22 Aug 17:48
@rtg0795 rtg0795
v3.11.3
b491c86
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Keras 3.11.3

What's Changed

Full Changelog: v3.11.2...v3.11.3

Contributors

rtg0795
Loading

Keras 3.11.2

11 Aug 21:12
@laxmareddyp laxmareddyp
v3.11.2
251ac34
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Keras 3.11.2

What's Changed

New Contributors

Full Changelog: v3.11.1...v3.11.2

Contributors

laxmareddyp
Loading

Keras 3.11.1

31 Jul 22:02
@rtg0795 rtg0795
v3.11.1
0e11071
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Keras 3.11.1

What's Changed

Full Changelog: v3.11.0...v3.11.1

Contributors

rtg0795
Loading

Keras 3.11.0

29 Jul 23:59
@fchollet fchollet
v3.11.0
7bf852c
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Keras 3.11.0

What's Changed

  • Add int4 quantization support.
  • Support Grain data loaders in fit()/evaluate()/predict().
  • Add keras.ops.kaiser function.
  • Add keras.ops.hanning function.
  • Add keras.ops.cbrt function.
  • Add keras.ops.deg2rad function.
  • Add keras.ops.layer_normalization function to leverage backend-specific performance optimizations.
  • Various bug fixes and performance optimizations.

Backend-specific changes

JAX backend

  • Support NNX library. It is now possible to use Keras layers and models as NNX modules.
  • Support shape -1 for slice op.

TensorFlow backend

  • Add support for multiple dynamic dimensions in Flatten layer.

OpenVINO backend

  • Add support for over 30 new backend ops.

New Contributors

Full Changelog: v3.10.0...v3.11.0

Contributors

iazzi, timovdk, and 6 other contributors
Loading

Keras 3.10.0

19 May 22:57
@fchollet fchollet
v3.10.0
3bedb9a
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Keras 3.10.0

New features

  • Add support for weight sharding for saving very large models with model.save(). It is controlled via the max_shard_size argument. Specifying this argument will split your Keras model weight file into chunks of this size at most. Use load_model() to reload the sharded files.
  • Add optimizer keras.optimizers.Muon
  • Add image preprocessing layer keras.layers.RandomElasticTransform
  • Add loss function keras.losses.CategoricalGeneralizedCrossEntropy (with functional version keras.losses.categorical_generalized_cross_entropy)
  • Add axis argument to SparseCategoricalCrossentropy
  • Add lora_alpha to all LoRA-enabled layers. If set, this parameter scales the low-rank adaptation delta during the forward pass.
  • Add activation function keras.activations.sparse_sigmoid
  • Add op keras.ops.image.elastic_transform
  • Add op keras.ops.angle
  • Add op keras.ops.bartlett
  • Add op keras.ops.blackman
  • Add op keras.ops.hamming
  • Add ops keras.ops.view_as_complex, keras.ops.view_as_real

PyTorch backend

  • Add cuDNN support for LSTM with the PyTorch backend

TensorFlow backend

  • Add tf.RaggedTensor support to Embedding layer
  • Add variable-level support for synchronization argument

OpenVINO backend

  • Add support for over 50 additional Keras ops in the OpenVINO inference backend!

New Contributors

Full Changelog: v3.9.0...v3.10.0

Contributors

superbobry, pschuh, and 29 other contributors
Loading

Keras 3.9.2

02 Apr 20:22
@rtg0795 rtg0795
v3.9.2
9067d80

Choose a tag to compare

View all tags
Keras 3.9.2

What's Changed

  • Fix Remat error when called with a model.

Full Changelog: v3.9.1...v3.9.2

Loading

Keras 3.9.1

27 Mar 17:17
@rtg0795 rtg0795
v3.9.1
54bdd19

Choose a tag to compare

View all tags
Keras 3.9.1

What's Changed

  • Fix flash attention TPU error
  • Fix incorrect argument in JAX flash attention.

Full Changelog: v3.9.0...v3.9.1

Loading

Keras 3.9.0

04 Mar 23:24
@fchollet fchollet
v3.9.0
eb1f844
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Keras 3.9.0

New features

  • Add new Keras rematerialization API: keras.RematScope and keras.remat. It can be used to turn on rematerizaliation for certain layers in fine-grained manner, e.g. only for layers larger than a certain size, or for a specific set of layers, or only for activations.
  • Increase op coverage for OpenVINO backend.
  • New operations:
    • keras.ops.rot90
    • keras.ops.rearrange (Einops-style)
    • keras.ops.signbit
    • keras.ops.polar
    • keras.ops.image.perspective_transform
    • keras.ops.image.gaussian_blur
  • New layers:
    • keras.layers.RMSNormalization
    • keras.layers.AugMix
    • keras.layers.CutMix
    • keras.layers.RandomInvert
    • keras.layers.RandomErasing
    • keras.layers.RandomGaussianBlur
    • keras.layers.RandomPerspective
  • Minor additions:
    • Add support for dtype argument to JaxLayer and FlaxLayer layers
    • Add boolean input support to BinaryAccuracy metric
    • Add antialias argument to keras.layers.Resizing layer.
  • Security fix: disallow object pickling in saved npz model files (numpy format). Thanks to Peng Zhou for reporting the vulnerability.

New Contributors

Full Changelog: v3.8.0...v3.9.0

Contributors

jurca, ibraaaa, and 11 other contributors
Loading

Keras 3.8.0

07 Jan 18:27
@fchollet fchollet
v3.8.0
fbf0af7
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

Choose a tag to compare

View all tags
Keras 3.8.0

New: OpenVINO backend

OpenVINO is now available as an infererence-only Keras backend. You can start using it by setting the backend field to "openvino" in your keras.json config file.

OpenVINO is a deep learning inference-only framework tailored for CPU (x86, ARM), certain GPUs (OpenCL capable, integrated and discrete) and certain AI accelerators (Intel NPU).

Because OpenVINO does not support gradients, you cannot use it for training (e.g. model.fit()) -- only inference. You can train your models with the JAX/TensorFlow/PyTorch backends, and when trained, reload them with the OpenVINO backend for inference on a target device supported by OpenVINO.

New: ONNX model export

You can now export your Keras models to the ONNX format from the JAX, TensorFlow, and PyTorch backends.

Just pass format="onnx" in your model.export() call:

# Export the model as a ONNX artifact
model.export("path/to/location", format="onnx")

# Load the artifact in a different process/environment
ort_session = onnxruntime.InferenceSession("path/to/location")

# Run inference
ort_inputs = {
    k.name: v for k, v in zip(ort_session.get_inputs(), input_data)
}
predictions = ort_session.run(None, ort_inputs)

New: Scikit-Learn API compatibility interface

It's now possible to easily integrate Keras models into Sciki-Learn pipelines! The following wrapper classes are available:

  • keras.wrappers.SKLearnClassifier: implements the sklearn Classifier API
  • keras.wrappers.SKLearnRegressor: implements the sklearn Regressor API
  • keras.wrappers.SKLearnTransformer: implements the sklearn Transformer API

Other feature additions

  • Add new ops:
    • Add keras.ops.diagflat
    • Add keras.ops.unravel_index
  • Add new activations:
    • Add sparse_plus activation
    • Add sparsemax activation
  • Add new image augmentation and preprocessing layers:
    • Add keras.layers.RandAugment
    • Add keras.layers.Equalization
    • Add keras.layers.MixUp
    • Add keras.layers.RandomHue
    • Add keras.layers.RandomGrayscale
    • Add keras.layers.RandomSaturation
    • Add keras.layers.RandomColorJitter
    • Add keras.layers.RandomColorDegeneration
    • Add keras.layers.RandomSharpness
    • Add keras.layers.RandomShear
  • Add argument axis to tversky loss

JAX specific changes

  • Add support for JAX named scope

TensorFlow specific changes

  • Make keras.random.shuffle XLA compilable

PyTorch specific changes

  • Add support for model.export() and keras.export.ExportArchive with the PyTorch backend, supporting both the TF SavedModel format and the ONNX format.

New Contributors

Full Changelog: v3.7.0...v3.8.0

Contributors

adrinjalali, punkeel, and 11 other contributors
Loading