Skip to content
Useful extra functionality for TensorFlow maintained by SIG-addons
Branch: master
Clone or download
seanpmorgan and facaiy FIX: Package seq2seq (#101)
* DOC: Add pip install

* FIX: Include seq2seq in binary package
Latest commit 7fe6e6c Mar 21, 2019
Type Name Latest commit message Commit time
Failed to load latest commit information.
.github/ISSUE_TEMPLATE Issue templates (#47) Mar 2, 2019
static DOC: use logo for SIG/addons (#93) Mar 16, 2019
tensorflow_addons FIX: Package seq2seq (#101) Mar 21, 2019
tools Adding a GPU test script. (#73) Mar 9, 2019
.gitignore Directory structure for discussion Jan 4, 2019
BUILD BUILD: Setup for release (#62) Mar 4, 2019
LICENSE Directory structure for discussion Jan 4, 2019 CLN: Move links (#100) Mar 21, 2019 introduction about coding style (#69) Mar 5, 2019
WORKSPACE Directory structure for discussion Jan 4, 2019

PyPI Status Badge Gitter chat

Official Builds

Build Type Status
Linux Py2 CPU Status
Linux Py3 CPU Status
Linux Py2 GPU Status
Linux Py3 GPU Status

TensorFlow Addons is a repository of contributions that conform to well-established API patterns, but implement new functionality not available in core TensorFlow. TensorFlow natively supports a large number of operators, layers, metrics, losses, and optimizers. However, in a fast moving field like ML, there are many interesting new developments that cannot be integrated into core TensorFlow (because their broad applicability is not yet clear, or it is mostly used by a smaller subset of the community).


Subpackage Maintainers Contact Info
tfa.activations SIG-Addons
tfa.layers SIG-Addons
tfa.losses SIG-Addons
tfa.optimizers SIG-Addons
tfa.seq2seq Google @qlzh727

Core Concepts

Standardized API within Subpackages

User experience and project maintainability are core concepts in TF-Addons. In order to achieve these we require that our additions conform to established API patterns seen in core TensorFlow.

Periodic Evaluation of Subpackages

Based on the nature of this repository, there will be contributions that in time become dated and unused. In order to keep the project maintainable, SIG-Addons will perform periodic reviews and deprecate contributions which will be slated for removal. More information will be available after we submit a formal request for comment.


See tensorflow_addons/examples/ for end-to-end examples of various addons.


Stable Builds

To install the latest version, run the following:

pip install tensorflow-addons

Note: You will also need TensorFlow 2.0 or higher.

To use addons:

import tensorflow as tf
import tensorflow_addons as tfa

Installing from Source

You can also install from source. This requires the Bazel build system.

git clone
cd addons

# This script links project with TensorFlow dependency

bazel build build_pip_pkg
bazel-bin/build_pip_pkg artifacts

pip install artifacts/tensorflow_addons-*.whl


TF-Addons is a community led open source project. As such, the project depends on public contributions, bug-fixes, and documentation. Please see contribution guidelines for a guide on how to contribute. This project adheres to TensorFlow's code of conduct. By participating, you are expected to uphold this code.



Apache License 2.0

You can’t perform that action at this time.