Package Exports

stargrad
stargrad/dist/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (stargrad) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

StarGrad

StarGrad is a powerful JavaScript library that provides automatic gradient calculation and mathematical tools, inspired by PyTorch's functionality. It's designed to make deep learning and mathematical computations more accessible to JavaScript developers.

Features

Automatic gradient calculation
Tensor operations similar to PyTorch
Mathematical operations and functions
GPU acceleration support (coming soon)
TypeScript support

Installation

You can install StarGrad using npm:

npm install stargrad

Quick Start

Import StarGrad in your project:

import { Tensor } from 'stargrad';

// Create a tensor
const x = new Tensor([1, 2, 3]);

// Perform operations
const y = x.mul(2);  // Multiply by 2
const z = y.add(1);  // Add 1

// Calculate gradients
z.backward();

Documentation

Core Concepts

Tensors: The fundamental data structure in StarGrad
Autograd: Automatic gradient calculation system
Operations: Mathematical operations on tensors

Basic Operations

// Create tensors
const a = new Tensor([1, 2, 3]);
const b = new Tensor([4, 5, 6]);

// Basic arithmetic
const sum = a.add(b);
const product = a.mul(b);
const quotient = a.div(b);

// Matrix operations
const matrix = new Tensor([[1, 2], [3, 4]]);
const transpose = matrix.transpose();

Contributing

We welcome contributions! Please feel free to submit a Pull Request.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Support

If you encounter any issues or have questions, please open an issue on our GitHub repository.