Starting with the Machine Learning Crash Course in February, Google has released a number of tools and resources for developers to learn and integrate artificial intelligence. Seedbank is the latest and a home to interactive ML examples that run in the web and can be quickly edited.

Shared by the TensorFlow team on Friday, Seedbank is an online collection of various projects from Google — named “Seeds” — that showcase machine learning’s various uses and capabilities.

Discovering and getting started with Machine Learning can be daunting. Perhaps you have a vague project idea and are looking for a place to start and adapt from. Or you’re looking for inspiration and want to get a sense of what’s possible.

One key aspect to Seedbank is how all the examples run right in your browser with “no set-up required.” It takes advantage of Colaboratory — Google’s hosted Jupyter notebook environment — that allows code to run directly in the browser with the company providing a free GPU backend.

On the new site, you can search for Colab-powered machine learning examples, with top-level categories like Images & Video, Sounds & Music, and Text & Language.

Each seed has a preview that lets you quickly assess if you want to explore further. Once you click through to the Colab notebook, you’ll be immediately connected to a GPU kernel and can start working through the example or tutorial. This allows for fast raining and inference.

Afterwards, users can edit the notebooks, save copies to Google Drive, and share any edited projects with friends. At the moment, only notebooks published by Google are listed, though user-generated content could be indexed in the future.


Check out 9to5Google on YouTube for more news:

About the Author