|
gptkbp:instanceOf
|
gptkb:model
|
|
gptkbp:architecture
|
gptkb:transformation
|
|
gptkbp:author
|
gptkb:Ilya_Sutskever
gptkb:Aditya_Ramesh
gptkb:Chris_Hallacy
gptkb:Gabriel_Goh
gptkb:Girish_Sastry
gptkb:Pamela_Mishkin
gptkb:Sandhini_Agarwal
gptkb:Jack_Clark
gptkb:Alec_Radford
gptkb:Amanda_Askell
gptkb:Jong_Wook_Kim
gptkb:Miles_Brundage
gptkb:Miranda_Chen
|
|
gptkbp:developedBy
|
gptkb:OpenAI
|
|
gptkbp:embeddingDimension
|
512
|
|
gptkbp:fullName
|
gptkb:Contrastive_Language–Image_Pre-training
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
OpenAI CLIP
|
|
gptkbp:imageEncoder
|
gptkb:ResNet
gptkb:Vision_Transformer_(ViT)
|
|
gptkbp:influenced
|
multimodal AI research
image generation models
vision-language models
|
|
gptkbp:input
|
gptkb:illustrator
gptkb:text
|
|
gptkbp:inputImageSize
|
224x224 pixels
|
|
gptkbp:language
|
English
|
|
gptkbp:license
|
gptkb:MIT_License
|
|
gptkbp:memiliki_tugas
|
image classification
zero-shot learning
image-text retrieval
|
|
gptkbp:notableFor
|
multimodal learning
zero-shot image classification
|
|
gptkbp:notablePublication
|
gptkb:Learning_Transferable_Visual_Models_From_Natural_Language_Supervision
|
|
gptkbp:openSource
|
true
|
|
gptkbp:output
|
gptkb:dictionary
embedding
|
|
gptkbp:paperPublicationDate
|
2021-01-05
|
|
gptkbp:pretrainedWeightsAvailable
|
true
|
|
gptkbp:publishedIn
|
gptkb:arXiv
|
|
gptkbp:releaseYear
|
2021
|
|
gptkbp:repository
|
https://github.com/openai/CLIP
|
|
gptkbp:supportsFewShot
|
true
|
|
gptkbp:supportsTransferLearning
|
true
|
|
gptkbp:supportsZeroShot
|
true
|
|
gptkbp:textEncoder
|
gptkb:transformation
|
|
gptkbp:trainer
|
400 million image-text pairs
|
|
gptkbp:trainingDataSource
|
publicly available internet data
|
|
gptkbp:usedIn
|
gptkb:DALL-E
gptkb:Midjourney
gptkb:Stable_Diffusion
|
|
gptkbp:bfsParent
|
gptkb:OpenAI_DALL-E
|
|
gptkbp:bfsLayer
|
6
|