Module: tf.keras.utils

Modules

experimental module

legacy module

Classes

class CustomObjectScope: Exposes custom classes/functions to Keras deserialization internals.

class FeatureSpace: One-stop utility for preprocessing and encoding structured data.

class GeneratorEnqueuer: Builds a queue out of a data generator.

class OrderedEnqueuer: Builds a Enqueuer from a Sequence.

class Progbar: Displays a progress bar.

class Sequence: Base object for fitting to a sequence of data, such as a dataset.

class SequenceEnqueuer: Base class to enqueue inputs.

class SidecarEvaluator: A class designed for a dedicated evaluator task.

class StepsPerExecutionTuner: Steps per execution tuner class.

class TimedThread: Time-based interval Threads.

class custom_object_scope: Exposes custom classes/functions to Keras deserialization internals.

Functions

array_to_img(...): Converts a 3D Numpy array to a PIL Image instance.

audio_dataset_from_directory(...): Generates a tf.data.Dataset from audio files in a directory.

deserialize_keras_object(...): Retrieve the object by deserializing the config dict.

disable_interactive_logging(...): Turn off interactive logging.

enable_interactive_logging(...): Turn on interactive logging.

get_custom_objects(...): Retrieves a live reference to the global dictionary of custom objects.

get_file(...): Downloads a file from a URL if it not already in the cache.

get_registered_name(...): Returns the name registered to an object within the Keras framework.

get_registered_object(...): Returns the class associated with name if it is registered with Keras.

get_source_inputs(...): Returns the list of input tensors necessary to compute tensor.

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

img_to_array(...): Converts a PIL Image instance to a Numpy array.

is_interactive_logging_enabled(...): Check if interactive logging is enabled.

load_img(...): Loads an image into PIL format.

model_to_dot(...): Convert a Keras model to dot format.

normalize(...): Normalizes a Numpy array.

pack_x_y_sample_weight(...): Packs user-provided data into a tuple.

pad_sequences(...): Pads sequences to the same length.

plot_model(...): Converts a Keras model to dot format and save to a file.

register_keras_serializable(...): Registers an object with the Keras serialization framework.

save_img(...): Saves an image stored as a Numpy array to a path or file object.

serialize_keras_object(...): Retrieve the config dict by serializing the Keras object.

set_random_seed(...): Sets all random seeds for the program (Python, NumPy, and TensorFlow).

split_dataset(...): Split a dataset into a left half and a right half (e.g. train / test).

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.

to_categorical(...): Converts a class vector (integers) to binary class matrix.

to_ordinal(...): Converts a class vector (integers) to an ordinal regression matrix.

unpack_x_y_sample_weight(...): Unpacks user-provided data tuple.

warmstart_embedding_matrix(...): Warm start embedding matrix with changing vocab.