Metatensor#

Metatensor is a specialized data storage format for all your atomistic machine learning needs, and more. Think numpy ndarray or pytorch Tensor equipped with extra metadata for atomic โ€” and other particles โ€” systems.

๐Ÿš€ Getting started

Install the right version of metatensor for your programming language! The core of this library is written in Rust and we provide API for C, C++, and Python.

๐Ÿ’ก What is metatensor

Learn about the core goals of metatensor, and what the library is about:

  • an exchange format for ML data;

  • a prototyping tool for new models;

  • an interface for atomistic simulations.

๐Ÿ› ๏ธ Core classes

Explore the core types of metatensor: TensorMap, TensorBlock and Labels, and discover how to used them.

๐Ÿ“ˆ Operations

Use operations to manipulate the core types of metatensor and write new algorithms operating on metatensorโ€™s sparse data.

๐Ÿ”ฅ TorchScript interface

Learn about the TorchScript version of metatensor, used to export and execute custom models inside non-Python software.

๐Ÿง‘โ€๐Ÿ’ป Learning utilities

Use the utility class with the same API as torch or scikit-learn to train models using metatensor!

โš›๏ธ Running atomistic simulations

Learn about the facilities provided to define atomistic models, and use them to run molecular dynamics simulations and more!