https://github.com/pit-ray/vim-autograd

Automatic differentiation library written in pure Vim script.
https://github.com/pit-ray/vim-autograd

autograd deep-learning neural-network vim vim-autograd vim8 vim9 vim9script vimscript

Last synced: about 2 months ago
JSON representation

Automatic differentiation library written in pure Vim script.

• Host: GitHub
• URL: https://github.com/pit-ray/vim-autograd
• Owner: pit-ray
• License: mit
• Created: 2022-03-13T19:13:18.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2024-02-23T14:18:10.000Z (10 months ago)
• Last Synced: 2024-05-01T16:30:44.599Z (8 months ago)
• Topics: autograd, deep-learning, neural-network, vim, vim-autograd, vim8, vim9, vim9script, vimscript
• Language: Vim Script
• Homepage:
• Size: 269 KB
• Stars: 26
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

README

        
# vim-autograd

**Automatic differentiation library written in pure Vim script.**

[![test](https://github.com/pit-ray/vim-autograd/actions/workflows/test.yml/badge.svg?branch=main)](https://github.com/pit-ray/vim-autograd/actions/workflows/test.yml) [![test-vim9](https://github.com/pit-ray/vim-autograd/actions/workflows/test-vim9.yml/badge.svg?branch=vim9)](https://github.com/pit-ray/vim-autograd/actions/workflows/test-vim9.yml)

vim-autograd provides a foundation for automatic differentiation through the Define-by-Run style algorithm such as Chainer or PyTorch. Since it is written completely in pure Vim script, there are no dependencies.

This library allows us to create next-generation plugins with numerical computation of multidimensional arrays or deep learning using the gradient descent method.

## Installation

### Vim script

If you are using [vim-plug](https://github.com/junegunn/vim-plug), can install as follows.

```vim

Plug 'pit-ray/vim-autograd'

```

### Vim9 script

If you want to use the more efficient Vim9 script, please install the experimental [vim9 branch](https://github.com/pit-ray/vim-autograd/tree/vim9) implementation.

```vim

Plug 'pit-ray/vim-autograd', {'branch': 'vim9'}

```

## Usage

A computational graph is constructed by applying the provided differentiable functions to a Tensor object, and the gradient is calculated by backpropagating from the output.

```vim

function! s:f(x) abort

  " y = x^5 - 2x^3

  let y = autograd#sub(a:x.p(5), a:x.p(3).m(2))

  return y

endfunction

function! s:example() abort

  let x = autograd#tensor(2.0)

  let y = s:f(x)

  call y.backward()

  echo x.grad.data

endfunction

call s:example()

```

**Output**

```

[56.0]

```

The computational graph is automatically generated like the below.



## Examples

- [Basic differentiation and computational graph visualization](examples/README.md#simplest-differentiation)

- [Higher-order differentiation using double-backprop](examples/README.md#higher-order-differentiation)

- [Classification using deep learning](examples/README.md#classification-using-deep-learning)

## Related posts

- https://zenn.dev/pitray/articles/482e89ddff329c

## References

- [oreilly-japan/deep-learning-from-scratch-3](https://github.com/oreilly-japan/deep-learning-from-scratch-3)

- [chainer/chainer](https://github.com/chainer/chainer)

- [pytorch/pytorch](https://github.com/pytorch/pytorch)

- [numpy/numpy](https://github.com/numpy/numpy)

- [mattn/vim-brain](https://github.com/mattn/vim-brain)

## License

This library is provided by **MIT License**.

## Author

- pit-ray