npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

js-pytorch

v0.7.2

Published

A JavaScript library like PyTorch, built from scratch.

Downloads

307

Readme

PyTorch in JavaScript

  • JS-PyTorch is a Deep Learning JavaScript library built from scratch, to closely follow PyTorch's syntax.
  • This library has GPU support, using GPU.js.
  • If you want to run it yourself, check out the Documentation.
  • Try out the Web Demo!

Note: You can install the package locally with: npm install js-pytorch

1.Table of Contents

2. Installation

  • On MacOS, Windows, and Ubuntu, you can install the library with npm install js-pytorch.
  • On Windows, if you run into an error, you might need to install the latest version of Visual Studio, including the "Desktop development with C++" workload.
  • To run in the Browser, npm install the latest version of JS-PyTorch, and link the distribution files in your HTML file:
<script src="./node_modules/js-pytorch/dist/utils.js"></script>
<script type="module">
  import { torch } from './node_modules/js-pytorch/dist/js-pytorch-browser.js';
  window.torch = torch;
</script>
  • After that, you can use JS-PyTorch freely in any <script> in your HTML file.

3. Running it Yourself

Simple Autograd Example:

const { torch } = require("js-pytorch");

// Pass device as an argument to a Tensor or nn.Module (same as PyTorch):
const device = 'gpu';

// Instantiate Tensors:
let x = torch.randn([8, 4, 5]);
let w = torch.randn([8, 5, 4], true, device);
let b = torch.tensor([0.2, 0.5, 0.1, 0.0], true);

// Make calculations:
let out = torch.matmul(x, w);
out = torch.add(out, b);

// Compute gradients on whole graph:
out.backward();

// Get gradients from specific Tensors:
console.log(w.grad);
console.log(b.grad);

Complex Autograd Example (Transformer):

const { torch } = require("js-pytorch");
const nn = torch.nn;
const optim = torch.optim;
const device = 'gpu';

// Define training hyperparameters:
const vocab_size = 52;
const hidden_size = 32;
const n_timesteps = 16;
const n_heads = 4;
const dropout_p = 0;
const batch_size = 8;

// Create Transformer decoder Module:
class Transformer extends nn.Module {
  constructor(vocab_size, hidden_size, n_timesteps, n_heads, dropout_p, device) {
    super();
    // Instantiate Transformer's Layers:
    this.embed = new nn.Embedding(vocab_size, hidden_size);
    this.pos_embed = new nn.PositionalEmbedding(n_timesteps, hidden_size);
    this.b1 = new nn.Block(hidden_size, hidden_size, n_heads, n_timesteps, dropout_p, device);
    this.b2 = new nn.Block(hidden_size, hidden_size, n_heads, n_timesteps, dropout_p, device);
    this.ln = new nn.LayerNorm(hidden_size);
    this.linear = new nn.Linear(hidden_size, vocab_size, device);
  }

  forward(x) {
    let z;
    z = torch.add(this.embed.forward(x), this.pos_embed.forward(x));
    z = this.b1.forward(z);
    z = this.b2.forward(z);
    z = this.ln.forward(z);
    z = this.linear.forward(z);
    return z;
  }
}

// Instantiate your custom nn.Module:
const model = new Transformer(vocab_size, hidden_size, n_timesteps, n_heads, dropout_p, device);

// Define loss function and optimizer:
const loss_func = new nn.CrossEntropyLoss();
const optimizer = new optim.Adam(model.parameters(), (lr = 5e-3), (reg = 0));

// Instantiate sample input and output:
let x = torch.randint(0, vocab_size, [batch_size, n_timesteps, 1]);
let y = torch.randint(0, vocab_size, [batch_size, n_timesteps]);
let loss;

// Training Loop:
for (let i = 0; i < 40; i++) {
  // Forward pass through the Transformer:
  let z = model.forward(x);

  // Get loss:
  loss = loss_func.forward(z, y);

  // Backpropagate the loss using torch.tensor's backward() method:
  loss.backward();

  // Update the weights:
  optimizer.step();

  // Reset the gradients to zero after each training step:
  optimizer.zero_grad();

  // Print loss at every iteration:
  console.log(`Iter ${i} - Loss ${loss.data[0].toFixed(4)}`)
}

Saving and Loading models:

// Instantiate your model:
const model = new Transformer(vocab_size, hidden_size, n_timesteps, n_heads, dropout_p);

// Train the model:
trainModel(model);

// Save model to JSON file:
torch.save(model, 'model.json')

// To load, instantiate placeHolder using the original model's architecture:
const placeHolder = new Transformer(vocab_size, hidden_size, n_timesteps, n_heads, dropout_p);

// Load weights into placeHolder:
const newModel = torch.load(placeHolder, 'model.json')

4. Distribution & Devtools

  • Build for Distribution by running npm run build. CJS and ESM modules and index.d.ts will be output in the dist/ folder.
  • Check the Code with ESLint at any time, running npm run lint.
  • Run tests run npm test.
  • Improve Code Formatting with prettier, running npm run prettier.
  • Performance Benchmarks are also included in the tests/benchmarks/ directory. Run all benchmarks with npm run bench and save new benchmarks with npm run bench:update.

5. Future Work

  • This package is not as optimized as PyTorch yet, but I tried making it more interpretable. Efficiency improvements are incoming!
  • Feel free to contribute! Create a merge request to the develop branch, and also feel free to reach out. I'll try to answer as soon as possible.
  • Hope you enjoy!