# Additional API references

This section contains additional collections of API reference pages for
projects and packages separate from the `tensorflow` package, but that
do not have dedicated subsite pages.

## The TensorFlow Models repository

The [TensorFlow Models repository](https://github.com/tensorflow/models)
provides implementations of state-of-the-art (SOTA) models.

The [official/projects](https://github.com/tensorflow/models/tree/master/official)
directory contains a collection of SOTA models that use TensorFlow's
high-level API. They are intended to be well-maintained, tested, and kept
up-to-date with the latest TensorFlow API.

The library code used to build and train these models is available as a pip
package. You can install it using:

    $ pip install tensorflow-models-official  # For the latest release
    $ #or
    $ pip install tf-models-nightly # For the nightly build

To install the package from source, refer to
[these instructions](https://github.com/tensorflow/models#method-2-clone-the-source).

The `tensorflow-models-official` pip package contains two top-level modules:
`tensorflow_models` and [`orbit`](https://www.tensorflow.org/api_docs/python/orbit). You can import them with:

    import tensorflow_models as tfm
    import orbit

### Tensorflow Models

[API reference](https://tensorflow.org/api_docs/python/tfm).

The `tensorflow_models` module handles building models and configuring training.
Application-specific functionality is available under [`tfm.vision`](https://www.tensorflow.org/api_docs/python/tfm/vision)
and [`tfm.nlp`](https://www.tensorflow.org/api_docs/python/tfm/nlp).

### Orbit

[API reference](https://tensorflow.org/api_docs/python/orbit).

The [`orbit`](https://www.tensorflow.org/api_docs/python/orbit) module defines a flexible and lightweight library for writing
customized training loop code in TensorFlow. Orbit is flexible about the type of
models it works with. You can use Orbit to train Keras
Models (as an alternative to Keras' [`Model.fit`](https://www.tensorflow.org/api_docs/python/tf/keras/Model#fit)), but you don't have to use
Keras at all. Orbit integrates seamlessly with [`tf.distribute`](https://www.tensorflow.org/api_docs/python/tf/distribute) and
supports running on different device types (CPU, GPU, and TPU).

## TensorFlow Compression

[API reference](https://tensorflow.org/api_docs/python/tfc).

The
[TensorFlow Compression repository](https://github.com/tensorflow/compression)
implements learnable compression algorithms that can be used to efficiently
compress your data or models.

On Linux and Mac OS, the package can be installed with pip:

    pip install tensorflow_compression

To install from source refer to [these instructions](https://github.com/tensorflow/compression/blob/master/README.md#building-pip-packages).