# 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`

Implemented Tensor Operations:

- [Add](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L346-L401) - [Subtract](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L404-L438) - [Multiply](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L441-L496) - [Divide](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L498-L557) - [Matrix Multiply](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L560-L621) - [Power](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L625-L663) - [Square Root](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L666-L704) - [Exponentiate](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#706-L744) - [Log](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L746-L785) - [Sum](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L790-L842) - [Mean](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L844-L894) - [Variance](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L896-L949) - [Transpose](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L953-L1008) - [At](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L1010-L1060) - [MaskedFill](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L1062-L1095) - [Reshape](https://github.com/eduardoleao052/js-torch/blob/07c1286867b952f32c0e904033214253e8812090/src/tensor.js#L1097-L1129)

Implemented Deep Learning Layers:

- [nn.Linear](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L60-L88) - [nn.MultiHeadSelfAttention](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L90-L163) - [nn.FullyConnected](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L165-L194) - [nn.Block](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L196-L226) - [nn.Embedding](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L231-L260) - [nn.PositionalEmbedding](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L262-L291) - [nn.ReLU](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L296-L325) - [nn.Softmax](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L327-L346) - [nn.Dropout](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L351-L376) - [nn.LayerNorm](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L378-L397) - [nn.CrossEntropyLoss](https://github.com/eduardoleao052/js-torch/blob/a158c91db9775a88fae6ed2d0f76d6d8ee6f9d23/src/layers.js#L400-L441)

## 1.Table of Contents * [Installation](#2-installation) * [Running it Yourself](#3-Running-it-Yourself) * [Simple Autograd Example](#simple-autograd-example) * [Complex Autograd Example (Transformer)](#complex-autograd-example-transformer) * [Saving and Loading models](#saving-and-loading-models) * [Distribution & Devtools](#4-distribution--devtools) * [Future Work](#5-future-work) ## 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](https://visualstudio.microsoft.com/downloads/?cid=learn-navbar-download-cta), 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: ```html ``` - After that, you can use JS-PyTorch freely in any `