Skip to content

An introduction to attention mechanisms and the vision transformer

License

Notifications You must be signed in to change notification settings

joseph-nagel/attention-mechanism

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

55 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Attention mechanism

A short introduction to attention in deep neural networks is provided. The important components of the classical transformer architecture are discussed. Following this, a vision transformer (ViT) is implemented and briefly tested.

The scaled dot-product (cross) attention mechanism is visualized

Notebooks

Installation

pip install -e .

ViT training

python scripts/main.py fit --config config/vit_mnist.yaml
python scripts/main.py fit --config config/vit_fmnist.yaml

Releases

No releases published

Packages

No packages published