OussamaLay

vit-pytorch

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

vision_transformer

pytorch-deep-learning

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

impulse_init

Convolutional Initialization for Data-Efficient Vision Transformers

ViT_Attention_Map_Visualization

ViT Attention map visualization (using Custom ViT and Pytorch timm module)

vision_transformers_googleio_extended

For Google IO extended talk Silicon Valley

cv-forum-2022-q4

Notes on Transformers in computer vision and deep learning.