Module chinese_clip 

Chinese contrastive Language-Image Pre-Training

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

• 💻 GH Link
• 💻 Transformers Python reference implementation

Modules

text_model

Chinese contrastive Language-Image Pre-Training

vision_model

Chinese contrastive Language-Image Pre-Training

Structs

ChineseClipConfig

ChineseClipModel

Enums

Activation

EncoderConfig

Functions

div_l2_norm