Fast intro to multi-modal ML with OpenAI’s CLIP

OpenAI’s CLIP is “multi-modal” model capable of understanding the relationships and concepts between both text and images. As we’ll see, CLIP is very capable, and when used via the Hugging Face library, could not be easier to work with.

Article:https://towardsdatascience.com/quick-fire-guide-to-multi-modal-ml-with-openais-clip-2dad7e398ac0

Friend Link (free access):https://towardsdatascience.com/quick-fire-guide-to-multi-modal-ml-with-openais-clip-2dad7e398ac0?sk=89bb2d8b8e583ed109d8a05e00366645

70% Discount on the NLP With Transformers in Python course:https://bit.ly/3DFvvY5

Subscribe for Article and Video Updates!https://jamescalam.medium.com/subscribehttps://medium.com/@jamescalam/membership

Discord:https://discord.gg/c5QtDB9RAP

00:00 Intro00:15 What is CLIP?02:13 Getting started05:38 Creating text embeddings07:23 Creating image embeddings10:26 Embedding a lot of images15:08 Text-image similarity search21:38 Alternative image and text search

The post Fast intro to multi-modal ML with OpenAI’s CLIP appeared first on AIPressRoom.