To build a content based image retrieval system that retrieves similar images matching the search image
I trained a VGG model to give embeddings for images of Fashion dataset. Then used KNN to give similar images based on the embeddings of the search Image.
Add the folder of your images and create a csv with image paths like styles.csv. Open two terminals, one for frontend and one for backend and run the the commands as follows:
npm run dev
python -m flask run