https://github.com/thefcraft/tftensor

tftensor is a tensor library implemented in Rust. It offers tensor operations, automatic differentiation, and supports basic neural network training functionalities.
https://github.com/thefcraft/tftensor

deep-learning-framework nn-from-scratch python-rust

Last synced: 7 days ago
JSON representation

tftensor is a tensor library implemented in Rust. It offers tensor operations, automatic differentiation, and supports basic neural network training functionalities.

• Host: GitHub
• URL: https://github.com/thefcraft/tftensor
• Owner: thefcraft
• Created: 2024-08-11T13:07:49.000Z (3 months ago)
• Default Branch: master
• Last Pushed: 2024-08-26T18:47:04.000Z (3 months ago)
• Last Synced: 2024-08-26T22:03:01.024Z (3 months ago)
• Topics: deep-learning-framework, nn-from-scratch, python-rust
• Language: Rust
• Homepage:
• Size: 481 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# `tftensor`: A Rust-based Tensor Library with Automatic Differentiation

`tftensor` is a tensor library implemented in Rust, designed to be a lightweight and efficient alternative to libraries like NumPy and PyTorch. It offers tensor operations, automatic differentiation, and supports basic neural network training functionalities.

## Features

- **Tensor Operations**: Support for a wide range of tensor operations including reshaping, slicing, and mathematical operations.

- **Statistical Operations**: Compute mean, sum, max, and min along specified dimensions.

- **Automatic Differentiation**: Built-in support for automatic gradient computation, making it suitable for machine learning and neural network training.

- **Random Number Generation**: Functions to generate tensors with random values, zeros, ones, and filled with specific values.

- **Integration with Python**: Provides a Python interface through PyO3, allowing for easy integration and use in Python projects.

## Contributing

1. Fork the repository.

2. Create a new branch (`git checkout -b feature-branch`).

3. Make your changes.

4. Commit your changes (`git commit -am 'Add new feature'`).

5. Push to the branch (`git push origin feature-branch`).

6. Create a new Pull Request.

## License

This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.

## Acknowledgements

- [PyO3](https://pyo3.rs/) for Python bindings.

- Rust community for support and inspiration.

## Contact

If you have any questions or feedback, feel free to reach out to [[email protected]](mailto:[email protected]).