W3cubDocs

/TensorFlow 2.4

Module: tf.compat.v1.keras.experimental

Public API for tf.keras.experimental namespace.

Classes

class CosineDecay: A LearningRateSchedule that uses a cosine decay schedule.

class CosineDecayRestarts: A LearningRateSchedule that uses a cosine decay schedule with restarts.

class LinearCosineDecay: A LearningRateSchedule that uses a linear cosine decay schedule.

class LinearModel: Linear Model for regression and classification problems.

class NoisyLinearCosineDecay: A LearningRateSchedule that uses a noisy linear cosine decay schedule.

class PeepholeLSTMCell: Equivalent to LSTMCell class but adds peephole connections.

class SequenceFeatures: A layer for sequence input.

class WideDeepModel: Wide & Deep Model for regression and classification problems.

Functions

export_saved_model(...): Exports a tf.keras.Model as a Tensorflow SavedModel.

load_from_saved_model(...): Loads a keras Model from a SavedModel created by export_saved_model().

© 2020 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/versions/r2.4/api_docs/python/tf/compat/v1/keras/experimental