Statements (28)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
Vision Transformer model
|
| gptkbp:activatedBy |
gptkb:GELU
|
| gptkbp:application |
Image classification
|
| gptkbp:architecture |
gptkb:transformation
|
| gptkbp:attentionMechanism |
Self-attention
|
| gptkbp:developedBy |
gptkb:Google_Research
|
| gptkbp:hiddenSize |
768
|
| https://www.w3.org/2000/01/rdf-schema#label |
ViT-B
|
| gptkbp:input |
Image patches
|
| gptkbp:introducedIn |
2020
|
| gptkbp:level |
12
|
| gptkbp:notableFauna |
12
|
| gptkbp:notablePublication |
gptkb:An_Image_is_Worth_16x16_Words:_Transformers_for_Image_Recognition_at_Scale
|
| gptkbp:openSource |
gptkb:Hugging_Face_Transformers
timm |
| gptkbp:parameter |
86 million
|
| gptkbp:platform |
gptkb:TensorFlow
gptkb:PyTorch |
| gptkbp:relatedTo |
gptkb:ViT-H
gptkb:ViT-L |
| gptkbp:resolution |
224x224
|
| gptkbp:size |
16x16
|
| gptkbp:trainer |
gptkb:JFT-300M
ImageNet-21k |
| gptkbp:usedFor |
Fine-tuning
Transfer learning |
| gptkbp:bfsParent |
gptkb:Vision_Transformer
|
| gptkbp:bfsLayer |
6
|