# Module: tf.compat.v1.keras

<br />

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

Detailed documentation and user guides are available at
[keras.io](https://keras.io).

## Modules

[`activations`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/activations) module: Built-in activation functions.

[`applications`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/applications) module: Keras Applications are canned architectures with pre-trained weights.

[`backend`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/backend) module: Keras backend API.

[`callbacks`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/callbacks) module: Callbacks: utilities called at certain points during model training.

[`constraints`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/constraints) module: Constraints: functions that impose constraints on weight values.

[`datasets`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/datasets) module: Keras built-in datasets.

[`estimator`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/estimator) module: Keras estimator API.

[`experimental`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/experimental) module: Public API for tf.keras.experimental namespace.

[`initializers`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/initializers) module: Keras initializer serialization / deserialization.

[`layers`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/layers) module: Keras layers API.

[`losses`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/losses) module: Built-in loss functions.

[`metrics`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/metrics) module: Built-in metrics.

[`mixed_precision`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/mixed_precision) module: Public API for tf.keras.mixed_precision namespace.

[`models`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/models) module: Code for model cloning, plus model-related API entries.

[`optimizers`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/optimizers) module: Built-in optimizer classes.

[`preprocessing`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/preprocessing) module: Keras data preprocessing utils.

[`regularizers`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/regularizers) module: Built-in regularizers.

[`utils`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/utils) module: Keras utilities.

[`wrappers`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/compat/v1/keras/wrappers) module: Wrappers for Keras models, providing compatibility with other frameworks.

## Classes

[`class Model`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/keras/Model): `Model` groups layers into an object with training and inference features.

[`class Sequential`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/keras/Sequential): Linear stack of layers.

## Functions

[`Input(...)`](https://www.tensorflow.org/versions/r2.0/api_docs/python/tf/keras/Input): `Input()` is used to instantiate a Keras tensor.