Statements (20)
Predicate | Object |
---|---|
gptkbp:instanceOf |
Vision Transformer model
|
gptkbp:activatedBy |
gptkb:GELU
|
gptkbp:architecture |
gptkb:transformation
|
gptkbp:attentionHeads |
16
|
gptkbp:developedBy |
gptkb:Google_Research
|
gptkbp:hiddenSize |
1280
|
https://www.w3.org/2000/01/rdf-schema#label |
ViT-H
|
gptkbp:inputPatchSize |
16x16
|
gptkbp:level |
32
|
gptkbp:parameter |
632 million
|
gptkbp:pdf |
gptkb:An_Image_is_Worth_16x16_Words:_Transformers_for_Image_Recognition_at_Scale
|
gptkbp:publicationYear |
2021
|
gptkbp:relatedTo |
gptkb:ViT
gptkb:ViT-G gptkb:ViT-L |
gptkbp:trainer |
ImageNet-21k
|
gptkbp:usedFor |
computer vision
image classification |
gptkbp:bfsParent |
gptkb:Vision_Transformer
|
gptkbp:bfsLayer |
6
|