OussamaLay's starred repositories

vit-pytorch

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

Language:PythonLicense:MITStargazers:19105Issues:147Issues:261
Language:Jupyter NotebookLicense:Apache-2.0Stargazers:9840Issues:99Issues:203

pytorch-deep-learning

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

Language:Jupyter NotebookLicense:MITStargazers:9632Issues:108Issues:193

impulse_init

Convolutional Initialization for Data-Efficient Vision Transformers

Language:Jupyter NotebookLicense:MITStargazers:14Issues:1Issues:1

ViT_Attention_Map_Visualization

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

Language:Jupyter NotebookStargazers:13Issues:3Issues:0

vision_transformers_googleio_extended

For Google IO extended talk Silicon Valley

Language:Jupyter NotebookStargazers:8Issues:2Issues:0

cv-forum-2022-q4

Notes on Transformers in computer vision and deep learning.

Language:Jupyter NotebookLicense:MITStargazers:1Issues:2Issues:0