A minimalist neural networks library built on a tiny autograd engine. Very much inspired by the micrograd library created by Andrej Karpathy.

This project aims to:

• demonstrate automatic differentiation, a core concept of modern Deep Learning frameworks like PyTorch and TensorFlow;
• define a simple API for training neural nets, somehow mimicking Keras and PyTorch Ignite;
• follow good coding practices, including type annotations and unit tests.

The demo notebook showcases what pyfit is all about.

• Autograd engine [ source | tests ]
• Neural networks API [ source | tests ]
• Metrics [ source | tests ]
• Optimizers [ source | tests ]
• Data utilities [ source | tests ]
• Training API [ source | tests ]

pyfit uses the following tools:

• black for code formatting.
• pylint and mypy for linting.
• pytest for testing.

Run the following commands in project root folder to check the codebase.

> pylint pyfit/* tests/*  # linting (including type checks)
> mypy .  # type checks only
> pytest  # test suite