VIT
A simple implementation of Vision Transformer (VIT) (@lodjim)
Official site consultedSenegalese open-source projects
Last verified: 1 October 2026
Simple implementation of the Vision Transformer for image classification, with modifiable training parameters, run through main.py. Images must be square at 384 x 384 pixels. No license is stated.
Services
- Training through main.py
- Image classification
Sources
- VIT (Vision Transformer) (new tab), verified on 1 October 2026Official site consulted