#TFWorld TF 2.0 Challenge

TensorFlow 2.0 has arrived, with a focus on ease of use, developer productivity, and scalable, production-ready machine learning workloads. Some of the features you can expect to see in TF 2.0:

  • Easy model building with Keras and eager execution.
  • Robust model deployment in production on any platform.
  • Powerful experimentation for research.
  • Simplifying the API by cleaning up deprecated APIs and reducing duplication.
  • Have low-level control with the Keras Subclassing API and tf.Module.

What Should I Hack?

Use our official release of TensorFlow 2.0 to do something nifty: build a model, a mobile or web application, an art installation, or something else entirely! The sky is the limit - and creativity is encouraged. We're excited to see what you build!

Note: This release of TF 2.0 is a production release, on the bleeding edge of development. If you run into any snags or encounter any bugs, please submit an issue on GitHub.

View full rules

Eligibility

Developers of all ages, backgrounds, and skill levels are encouraged to submit projects. Teams may have between 1 and 6 participants. Participants are encouraged to expand the scope of an existing TensorFlow 1.x project, to migrate and continue work on a historic TensorFlow 1.x project; or to create an entirely new software solution using TensorFlow 2.0.

Applications may submit projects that integrate with other third-party SDKs, APIs, and services, provided the participant is authorized to use them. There are no restrictions on cloud service providers, operating systems, or hardware platforms. All participants will be obliged to work under the TensorFlow Code of Conduct.

Note: government officials, corporations, and employees of Google or DevPost are not eligible to win prizes, but may submit projects. See #TFWorld TF 2.0 Challenge terms for further restrictions.

Requirements

Build or migrate a functioning TensorFlow 2.0-powered solution!

  • (Optional) Submit a 2-5 minute demo video hosted on YouTube, Vimeo, or Youku. Your video should include a demo of your working application.
  • Please submit at least one image or screenshot of your solution.
  • Make sure all of your code has been uploaded to a public repo on GitHub, and a link to the repo has been included in your application.

All projects must be submitted by December 31st, 2019, at 11:45PM Pacific Time. Judging will take place during Google I/O, from January 1st through January 15th. Contest winners will be informed of their project's status on the evening of January 22nd.

Judges

Paige Bailey

Paige Bailey
TensorFlow Product Manager

Alexandre Passos

Alexandre Passos
TensorFlow Engineer

Martin Wicke

Martin Wicke
TensorFlow Manager

Kemal El Moujahid

Kemal El Moujahid
Director of Product Management

Judging Criteria

  • Creativity
    How original and innovative is the product? Is there already an existing model or software application with similar functionality? Does this project integrate deep learning in an innovative, unexpected way?
  • Technical Complexity
    Does the product integrate a large number of components? Is it widely useful, and scalable? Is the software application or model usable in a production setting?
  • Social Impact
    What kind of social or business value could this product deliver? How does this software application use deep learning to make the world a little bit better, and to positively impact people’s lives?

themes

  • Machine Learning/ AI
  • Social Good