https://github.com/SilasMarvin/dnns-from-scratch-in-zig
https://github.com/SilasMarvin/dnns-from-scratch-in-zig
Last synced: 11 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/SilasMarvin/dnns-from-scratch-in-zig
- Owner: SilasMarvin
- License: gpl-3.0
- Created: 2023-04-19T18:10:46.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2024-08-25T15:26:23.000Z (almost 2 years ago)
- Last Synced: 2024-11-30T02:45:39.167Z (over 1 year ago)
- Language: Zig
- Size: 25.4 KB
- Stars: 66
- Watchers: 3
- Forks: 7
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-zig - dnns-from-scratch-in-zig
- awesome-zig - SilasMarvin/dnns-from-scratch-in-zig - A very simple implementation of deep neural networks written in the Zig programming language. (Data & Science / Machine Learning Framework)
README
This repo is a very simple implementation of deep neural networks written in the Zig programming language.
It does not utilize tensors or any automatic differentiation library as it is only composed of fully connected feed forward layers.
To solve MNIST, create a new directory "data" in the root of the project, download the MNIST files from [http://yann.lecun.com/exdb/mnist/](http://yann.lecun.com/exdb/mnist/), and unzip and store the files in the "data" directory. Then run:
```
zig build run
```
If the above url is not working for you, checkout: [https://github.com/cvdfoundation/mnist](https://github.com/cvdfoundation/mnist).