Module: tf.keras.preprocessing

Utilities to preprocess data before training.

Deprecated: tf.keras.preprocessing APIs do not operate on tensors and are not recommended for new code. Prefer loading data with either tf.keras.utils.text_dataset_from_directory or tf.keras.utils.image_dataset_from_directory, and then transforming the output tf.data.Dataset with preprocessing layers. These approaches will offer better performance and intergration with the broader Tensorflow ecosystem. For more information, see the tutorials for loading text, loading images, and augmenting images, as well as the preprocessing layer guide.

Modules

image module: Utilies for image preprocessing and augmentation.

sequence module: Utilities for preprocessing sequence data.

text module: Utilities for text input preprocessing.

Functions

image_dataset_from_directory(...): Generates a tf.data.Dataset from image files in a directory.

text_dataset_from_directory(...): Generates a tf.data.Dataset from text files in a directory.

timeseries_dataset_from_array(...): Creates a dataset of sliding windows over a timeseries provided as array.