Implementation of the Keras API, the high-level API of TensorFlow.
Detailed documentation and user guides are available at keras.io.
Modules
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: Small NumPy datasets for debugging/testing.
estimator module: Keras estimator API.
experimental module: Public API for tf.keras.experimental namespace.
initializers module: Keras initializer serialization / deserialization.
layers module: Keras layers API.
losses module: Built-in loss functions.
metrics module: Built-in metrics.
mixed_precision module: Keras mixed precision API.
models module: Code for model cloning, plus model-related API entries.
optimizers module: Built-in optimizer classes.
preprocessing module: Provides keras data preprocessing utils to pre-process tf.data.Datasets before they are fed to the model.
regularizers module: Built-in regularizers.
utils module: Public API for tf.keras.utils namespace.
wrappers module: Public API for tf.keras.wrappers namespace.
Classes
class Model: Model groups layers into an object with training and inference features.
class Sequential: Sequential groups a linear stack of layers into a tf.keras.Model.
Functions
Input(...): Input() is used to instantiate a Keras tensor.