Intro to Multi-Modal ML with OpenAI's CLIP

Explore OpenAI's CLIP, a multi-modal model capable of understanding relationships between text and images, in this 23-minute tutorial. Learn how to use CLIP via the Hugging Face library to create text and image embeddings, perform text-image similarity searches, and explore alternative image and text search methods. Gain practical insights into multi-modal machine learning and discover the power of CLIP in bridging the gap between textual and visual data processing.

Intro
What is CLIP?
Getting started
Creating text embeddings
Creating image embeddings
Embedding a lot of images
Text-image similarity search
Alternative image and text search