Repository files navigation

Automatic differentiation library written in pure Vim script.

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.

If you are usingvim-plug, can install as follows.

Plug'pit-ray/vim-autograd'

If you want to use the more efficient Vim9 script, please install the experimentalvim9 branch implementation.

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

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.

function!s:f(x)abort" y = x^5 - 2x^3lety=autograd#sub(a:x.p(5),a:x.p(3).m(2))returnyendfunctionfunction!s:example()abortletx=autograd#tensor(2.0)lety=s:f(x)cally.backward()echox.grad.dataendfunctioncalls:example()

Output

[56.0]

The computational graph is automatically generated like the below.

• Basic differentiation and computational graph visualization
• Higher-order differentiation using double-backprop
• Classification using deep learning

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

• oreilly-japan/deep-learning-from-scratch-3
• chainer/chainer
• pytorch/pytorch
• numpy/numpy
• mattn/vim-brain

This library is provided byMIT License.

• pit-ray