About Keras Getting started Developer guides Code examples Keras 3 API documentation Keras 2 API documentation KerasTuner: Hyperparam Tuning KerasHub: Pretrained Models Getting started Developer guides API documentation Modeling API Model Architectures Tokenizers Preprocessing Layers Modeling Layers Samplers Metrics Pretrained models list
► KerasHub: Pretrained Models / API documentation / KerasHub Preprocessing Layers

KerasHub Preprocessing Layers

KerasHub preprocessing layers can be used to create custom preprocessing pipelines for pretrained models. Preprocessing layers are all compatible with tf.data, even when running on the jax and torch backends.

AudioConverter layer

  • AudioConverter class
  • from_preset method

ImageConverter layer

  • ImageConverter class
  • from_preset method

StartEndPacker layer

  • StartEndPacker class

MultiSegmentPacker layer

  • MultiSegmentPacker class

RandomSwap layer

  • RandomSwap class

RandomDeletion layer

  • RandomDeletion class

MaskedLMMaskGenerator layer

  • MaskedLMMaskGenerator class
KerasHub Preprocessing Layers
AudioConverter layer
ImageConverter layer
StartEndPacker layer
MultiSegmentPacker layer
RandomSwap layer
RandomDeletion layer
MaskedLMMaskGenerator layer
Terms | Privacy