3 releases

0.1.2 Jun 19, 2024
0.1.1 Jun 9, 2024
0.1.0 Jun 3, 2024

#403 in Machine learning

Download history 13/week @ 2024-09-15 21/week @ 2024-09-22

168 downloads per month

MIT license

505KB
2K SLoC

Poro

Professor Poro

Poro is a simple toy neural network library implemented in Rust. It is designed for educational purposes and provides basic functionality to create, train, and evaluate neural networks. This library is not intended for production use but serves as a learning tool for those interested in understanding the fundamentals of neural networks and their implementation.

Features

  • Basic neural network operations
  • Tensor manipulation
  • Support for custom layers and operations
  • Lightweight and easy to understand

Getting Started

Prerequisites

Ensure you have Rust installed on your system. You can install Rust using rustup.

Installation

To use Poro, add the following to your Cargo.toml:

[dependencies]
poro = "0.1.1"

Usage

Here is a simple example to get you started with Poro:

use Poro::model::Model;
use Poro::tensor::Tensor;
use Poro::operation::Operation;

fn main() {
    // Create a simple neural network
    let model = Model::new();

    // Define input tensor
    let input = Tensor::new(vec![1.0, 2.0, 3.0]);

    // Perform a forward pass
    let output = model.forward(input);

    // Print the output
    println!("{:?}", output);
}

Contributing

Contributions are welcome! Please feel free to submit a pull request or open an issue to discuss any changes or additions.

License

Poro is licensed under the MIT License. See the LICENSE file for more information.

Dependencies

~28MB
~650K SLoC