An open source project isn't just about the code, it's also about the community of users, developers, writers, researchers, and other contributors. You can help grow and support this community.
Many people ask questions about TensorFlow on Stack Overflow. Answering those questions and pointing people to the relevant documentation is a great service to the community.
Some users also ask support questions as GitHub issues. We try to discourage this, as GitHub issues are not the best place to ask for technical support. However, if you notice these issues, you are encouraged to answer them and point people to the relevant documentation.
The TensorFlow community has a number of formal and informal ways of keeping in touch.
The primary communication about work on TensorFlow happens in the TensorFlow repositories on GitHub. This is the place to discuss bugs, new features, and in-progress work.
Mailing lists are reserved for announcements and contributor conversation. They are not intended to provide technical support.
General TensorFlow lists
- email@example.com — All major releases and important announcements are sent to this mailing group. We recommend that you join this list if you depend on TensorFlow in any way.
- firstname.lastname@example.org — General discussion about TensorFlow development and direction.
- email@example.com — Discussion for developers who are contributing to TensorFlow.
- firstname.lastname@example.org — If you are interested in contributing to the TensorFlow documentation, join this mailing list.
- email@example.com — Discussion and collaboration around TensorFlow Hub.
- firstname.lastname@example.org — General discussion about Magenta development and direction.
- email@example.com — Community and collaboration around Swift for TensorFlow.
- firstname.lastname@example.org — Discussion and peer support for Tensor2Tensor.
- email@example.com — Announcements of new TensorFlow.js releases.
- firstname.lastname@example.org — Discussion and peer support for TensorFlow.js.
- email@example.com — Discussion and peer support for TensorFlow Lite.
- firstname.lastname@example.org — Discussion and peer support for TensorFlow Probability.
- email@example.com — Community discussion and support for TPU users.
We post regularly to the TensorFlow Blog, with content sourced from both TensorFlow developers and the broader community. If you would like to submit an article for review, please contact the TensorFlow Developer Relations team.
The Roadmap summarizes plans for upcoming additions to TensorFlow.
TensorFlow has many communities all over the world! For a complete listing, please refer to the Community section on the TensorFlow website.
Special Interest Groups (SIGs)
To enable focused collaboration on particular areas of TensorFlow, we host Special Interest Groups (SIGs). SIGs do their work in public. If you want to join and contribute, review the work of the group, and get in touch with the relevant SIG leader. Membership policies vary on a per-SIG basis.
As of January 2019, the current TF-SIGs are:
|SIG Addons||Maintains a repository of contributions that conform to well-established API patterns, but implement new functionality not available in core TensorFlow.|
|SIG Build||Focuses on issues surrounding building, packaging, and distribution of TensorFlow.|
|SIG IO||Works on support for file systems and formats other than those in core TensorFlow (such as Apache Ignite FS, or Apache Hadoop SequenceFile), as subclasses of tf.data.Dataset and TensorFlow filesystems.|
|SIG Networking||Maintains network fabrics and protocols not available in core TensorFlow.|
|SIG TensorBoard||Furthers the development and direction of TensorBoard and its plug-ins.|
|SIG Rust||Collaborates on the development of TensorFlow's Rust bindings.|
If you believe there is a strong need for a new SIG, please read the SIG playbook and get in touch with the TensorFlow Developer Relations Team.