Module: tf.keras

Defined in tensorflow/keras/

Implementation of the Keras API meant to be a high-level API for TensorFlow.

Detailed documentation and user guides are available at


activations module: Built-in activation functions.

applications module: Keras Applications are canned architectures with pre-trained weights.

backend module: Keras backend API.

callbacks module: Callbacks: utilities called at certain points during model training.

constraints module: Constraints: functions that impose constraints on weight values.

datasets module: Keras built-in datasets.

estimator module: Keras estimator API.

initializers module: Keras initializer classes (soon to be replaced with core TF initializers).

layers module: Keras layers API.

losses module: Built-in loss functions.

metrics module: Built-in metrics.

models module: Code for model cloning, plus model-related API entries.

optimizers module: Built-in optimizer classes.

preprocessing module: Keras data preprocessing utils.

regularizers module: Built-in regularizers.

utils module: Keras utilities.

wrappers module: Wrappers for Keras models, providing compatibility with other frameworks.


class Model: Model groups layers into an object with training and inference features.

class Sequential: Linear stack of layers.


Input(...): Input() is used to instantiate a Keras tensor.

Other Members