pyrus-nn

Rust API 文档

使用Rust编写的轻量级神经网络框架，具有薄的Python绑定。

• 功能

  • 将网络序列化为YAML & JSON！
    • Rust -> serde 兼容
    • Python -> network.to_dict() & Sequential.from_dict()
  • Python安装无需依赖
  • 无需安装外部系统库

• 缺点

  • 仅支持通用梯度下降。
  • 目前仅支持全连接（密集）层
  • 激活函数仅限于线性、tanh、sigmoid和softmax
  • 损失函数仅限于MSE、MAE、交叉熵和准确率

安装

Python

pip install pyrus-nn  # Has ZERO dependencies!

Rust

[dependencies]
pyrus-nn = "0.2.0"

从Python

from pyrus_nn.models import Sequential
from pyrus_nn.layers import Dense

model = Sequential(lr=0.001, n_epochs=10)
model.add(Dense(n_input=12, n_output=24, activation='sigmoid'))
model.add(Dense(n_input=24, n_output=1, activation='sigmoid'))

# Create some X and y, each of which must be 2d
X = [list(range(12)) for _ in range(10)]
y = [[i] for i in range(10)]  

model.fit(X, y)
out = model.predict(X)

从Rust

use ndarray::Array2;
use pyrus_nn::{network::Sequential, layers::Dense};


// Network with 4 inputs and 1 output.
fn main() {
    let mut network = Sequential::new(0.001, 100, 32, CostFunc::CrossEntropy);
    assert!(
        network.add(Dense::new(4, 5)).is_ok()
    );
    assert!(
        network.add(Dense::new(5, 6)).is_ok()
    );
    assert!(
        network.add(Dense::new(6, 4)).is_ok()
    );
    assert!(
        network.add(Dense::new(4, 1)).is_ok()
    );
    
    let X: Array2<f32> = ...
    let y: Array2<f32> = ...
    
    network.fit(X.view(), y.view());
    
    let yhat: Array2<f32> = network.predict(another_x.view());
}