elixir-nx/axon

This system is a high-level neural network library for Elixir that provides a comprehensive API for defining, training, and evaluating deep learning models. It supports a wide range of architectures, including vision, generative AI, time-series, and structured data models, with built-in infrastructure for mixed-precision training and serialization. The project is heavily documented with interactive notebooks and examples that demonstrate practical implementations of these capabilities.

This period focused on establishing a high-level neural network API and comprehensive training infrastructure within the Axon library. The work included adding core building blocks, mixed-precision support, and extensive test coverage, while also introducing a wide array of practical examples for vision, generative AI, and fraud detection.

8 changes

This period focused on expanding the Axon deep learning library with comprehensive examples, notebooks, and documentation. The work included adding multi-input/output model demonstrations, generative AI and vision notebooks, and detailed guides for model creation, serialization, and training loops. Additionally, test coverage was significantly improved for core components and fixtures.

12 changes

elixir-nx/axon was measured the same way every project in this corpus was: the same rubric, at a pinned commit, with the result published in full. Point the surveyor at a repository you know and see whether you agree with it.