Googles DeepMind announced today that it was open sourcing Sonnet, its object-oriented neural network library. Sonnet doesnt replace TensorFlow, its simply a higher-level library that meshes well with DeepMinds internal best-practices for research.
Specifically, DeepMind says in its blog post that the library is optimized to make it easier to switch between different models when conductingexperiments so that engineers dont have to upend their entire projects. To this avail, the team made changes to TensorFlow to make it easier toconsider models as hierarchies. DeepMind also added transparency tovariable sharing.
Its in DeepMinds own interest to open source Sonnet.If the community becomes acquainted with DeepMinds internal libraries, it will become easier for the group torelease models side-by-side with papers. Inversely, it also means the machine intelligence community can more feasibly contribute back by employing Sonnet in their own work.
I think @DeepMindAI is opensourcing Sonnet to make it easier for them to opensource models along with papers. A move in the right direction.
hardmaru (@hardmaru) April 7, 2017
DeepMind has been particularly active in open source in recent months. It is developing an open-source API to enable research to be done on StarCraft II. Back in December, the team released DeepMind Lab to catalyze generalized AI research much like OpenAIs Universe. Open-source projects even got their own home on the DeepMind website.
The library is available now on GitHub. The group plans to continue to release updates as it modifies itslibrary internally.