Add CLIP-Finder Submodule for Semantic Image Searches

fguzman82 commented 2 weeks ago

CLIP-Finder enables semantic offline searches of images from gallery photos using natural language descriptions or the camera.

Changes

Added CLIP-Finder submodule in the CLIP-Finder directory.

Motivation and Context

Inspired by the examples in coreml-examples, I would like to include this project. Adding this submodule will enhance the repository with advanced image and text similarity search capabilities based on MobileCLIP and FastViT, leveraging CoreML and on-device processing for efficient and private operations.

Checklist

[x] I have tested these changes locally.
[x] I have updated the documentation as needed.

FL33TW00D commented 2 weeks ago

@pcuenca for when you return :)

fguzman82 commented 3 days ago

The version used for the Pull Request is now outdated. I will make a new pull request with version 1.3.

huggingface / coreml-examples