AIPineconealmost 3 years ago
Multi-modal ML with OpenAI's CLIP
1 min read
OpenAI's CLIP model enables multi-modal machine learning by connecting images and text. The model learns visual concepts from natural language supervision, allowing zero-shot transfer to various tasks without task-specific training data.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI