Statements (18)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:convolutional_neural_network
|
| gptkbp:architecture |
gptkb:ResNet
gptkb:Vision_Transformer |
| gptkbp:developedBy |
gptkb:OpenAI
|
| https://www.w3.org/2000/01/rdf-schema#label |
CLIP image encoder
|
| gptkbp:input |
gptkb:illustrator
|
| gptkbp:language |
gptkb:Python
|
| gptkbp:openSource |
true
|
| gptkbp:output |
embedding vector
|
| gptkbp:partOf |
gptkb:CLIP
|
| gptkbp:platform |
gptkb:PyTorch
|
| gptkbp:relatedTo |
gptkb:CLIP_text_encoder
|
| gptkbp:releaseYear |
2021
|
| gptkbp:trainer |
400 million image-text pairs
|
| gptkbp:usedFor |
zero-shot image classification
image-text alignment |
| gptkbp:bfsParent |
gptkb:CLIP_text_encoder
|
| gptkbp:bfsLayer |
7
|