Statements (18)
Predicate | Object |
---|---|
gptkbp:instanceOf |
vision transformer model
|
gptkbp:architecture |
gptkb:transformation
|
gptkbp:citation |
hundreds (as of 2024)
|
gptkbp:developedBy |
gptkb:Google_Research
|
https://www.w3.org/2000/01/rdf-schema#label |
ViT-G
|
gptkbp:input |
gptkb:illustrator
|
gptkbp:introducedIn |
2022
|
gptkbp:notableFor |
large scale vision transformer
|
gptkbp:notablePublication |
Scaling Vision Transformers
|
gptkbp:parameter |
1.8 billion
|
gptkbp:relatedTo |
gptkb:ViT
gptkb:ViT-H gptkb:ViT-L |
gptkbp:trainer |
gptkb:ImageNet
JFT-4B |
gptkbp:usedFor |
image classification
|
gptkbp:bfsParent |
gptkb:Vision_Transformer
|
gptkbp:bfsLayer |
6
|