New
Keras 3.10.0
New features
- Add support for weight sharding for saving very large models with
model.save(). It is controlled via themax_shard_sizeargument. Specifying this argument will split your Keras model weight file into chunks of this size at most. Useload_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 versionkeras.losses.categorical_generalized_cross_entropy) - Add
axisargument toSparseCategoricalCrossentropy - Add
lora_alphato 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