Module clip 

Contrastive Language-Image Pre-Training

Contrastive Language-Image Pre-Training (CLIP) is an architecture trained on pairs of images with related texts.

• 💻 GH Link
• 💻 Transformers Python reference implementation
• 🤗 HF Model

Modules

text_model

Contrastive Language-Image Pre-Training

vision_model

Contrastive Language-Image Pre-Training

Structs

ClipConfig

ClipModel

Enums

EncoderConfig

Functions

div_l2_norm