Build creative, well-implemented, and impactful solutions with PyTorch.

WINNERS HAVE BEEN ANNOUNCED

Thank you to the machine learning enthusiasts who traveled from all over the globe to compete in the challenge! Head over to the submission gallery to check out the projects. 

Our winners in the hackathon were:

Best in Show learn2learn
Second Place HelloWorldNet: Discovering extrasolar planets with PyTorch
Third Place MineTorch
Honorable Mention Fonts Done Right
Honorable Mention Edu Glot
Honorable Mention Audimext - See what you hear !
Honorable Mention Unsupervised Representation Learning for Contextual Bandits
Honorable Mention PyTorch Falcon

Interested in building using PyTorch?

Register for the Global PyTorch Summer Hackathon and submit your project before September 16th! 

PyTorch is an open source machine learning framework that is used by both researchers and developers to build, train, and deploy ML systems that solve many different complex challenges. The PyTorch team invites you to hack with the PyTorch community to build innovative, impactful models, applications and other projects that create positive impact for businesses or people. 

PyTorch is continually evolving to make it easier and faster for researchers to go from research exploration to production deployment. Some of the PyTorch capabilities and tools you can work with for the hackathon include:

Be sure to check out these Resources before getting started.

Participants will have the opportunity to win over $12,000 in prizes. Good luck and get to hacking!

 

View full rules

Requirements

Main Requirement: Build a creative and well-implemented solution using PyTorch that can create a positive impact on businesses or people. The solution can be a machine learning model, an application, or a creative project such as art or music built with PyTorch.

Submit the following assets: 

  1. Demo video (optional) -. Your video should be around 1-2 minutes, include a demo of your working solution via a step-by-step visual demo, and be available in English. Be sure to explain how PyTorch was used to build your solution!
  2. Images. Please submit at least one image/screenshot of your working solution.
  3. Access. Provide a link to your publicly accessible code repository on GitHub or Bitbucket.

How to Enter:

  1. Enter your completed submission form BEFORE 3PM PDT August 9th. Late submissions will not be accepted. Devpost team will be available onsite to help with the submission process. 
  2. Ensure at least one member of your team is at your assigned table for the entire judging period in order to demo to the judges. You may be asked to demo more than once and if your team’s table is empty when the judges come by, you may be disqualified.

Judges

A panel of qualified judges from Facebook and PyTorch

A panel of qualified judges from Facebook and PyTorch

Judging Criteria

  • Quality of Idea
    Includes creativity and originality of the idea.
  • Implementation of the Idea
    Includes how well the idea was executed by the developer.
  • Potential Impact
    Includes the potential positive impact of the application, such as bettering the lives of people or environment, and accelerating business or research outcomes.

theme

  • Machine Learning/ AI