14 releases (9 breaking)

0.16.0 Jan 14, 2025
0.15.0 Oct 28, 2024
0.14.0 Aug 27, 2024
0.13.2 May 3, 2024
0.8.0 Jul 25, 2023

#654 in Machine learning

Download history 83/week @ 2024-11-29 285/week @ 2024-12-06 140/week @ 2024-12-13 64/week @ 2024-12-20 41/week @ 2024-12-27 102/week @ 2025-01-03 247/week @ 2025-01-10 282/week @ 2025-01-17 196/week @ 2025-01-24 214/week @ 2025-01-31 190/week @ 2025-02-07 207/week @ 2025-02-14 237/week @ 2025-02-21 180/week @ 2025-02-28 142/week @ 2025-03-07 154/week @ 2025-03-14

756 downloads per month
Used in 3 crates

MIT/Apache

1MB
19K SLoC

Importing Models

The Burn project supports the import of models from various frameworks, emphasizing efficiency and compatibility. Currently, it handles two primary model formats:

  1. ONNX: Facilitates direct import, ensuring the model's performance and structure are maintained.

  2. PyTorch: Enables the loading of PyTorch model weights into Burn’s native model architecture, ensuring seamless integration.

Contribution

Interested in contributing to burn-import? Check out our development guide for more information.


lib.rs:

burn-import is a crate designed to simplify the process of importing models trained in other machine learning frameworks into the Burn framework. This tool generates a Rust source file that aligns the imported model with Burn's model and converts tensor data into a format compatible with Burn.

Dependencies

~59–91MB
~2M SLoC