PyTorch-Scratch-Vision-Transformer-ViT icon indicating copy to clipboard operation
PyTorch-Scratch-Vision-Transformer-ViT copied to clipboard

Published 5 months ago • verified publisher icon s-chh
→

Metadata

Simple and easy to understand PyTorch implementation of Vision Transformer (ViT) from scratch, with detailed steps. Tested on common datasets like MNIST, CIFAR10, and more.

Results 2 PyTorch-Scratch-Vision-Transformer-ViT issues
Sort by recently updated
recently updated
newest added

Rotary Position Embedding

1 comment

I really enjoy reading your code; it is very clear and easy to understand, while also achieving top results in the benchmarks! I would like to explore [Rotary Position Embedding...

entron avatar entron

Model_weights

Hi, thanks a lot for your great work! May I kindly request your model weights, eg trained on MNIST, SVHN?

Darcyddx avatar Darcyddx

← Metadata

147
Stars
23
Forks
147
Watchers

Owner

verified publisher icon s-chh

Metadata

Simple and easy to understand PyTorch implementation of Vision Transformer (ViT) from scratch, with detailed steps. Tested on common datasets like MNIST, CIFAR10, and more.

Back