nickhamiltonn/efficient-vit-training

An implementation of the the methods outlined in the paper, "Training a Vision Transformer from scratch in less than 24 hours with 1 GPU"

This repository is a reimplementation of the proposed methods in Borealis AI's "Training a Vision Transformer from scratch in less than 24 hours with 1 GPU", as seen on arXiv (https://arxiv.org/abs/2211.05187#).