some confusion about fine-tunning CLIP

openai / CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

MIT License

24.55k stars 3.2k forks source link

some confusion about fine-tunning CLIP #427

Open SoulProficiency opened 6 months ago

SoulProficiency commented 6 months ago

dear official： 1.can we do zero-shot on coco dataset? 2.What are the minimum equipment requirements of fine-tunning CLIP with coco dataset？(default batch-size=32) 3.how to use prompt to infer a open dataset(object detection)？ Thanks