tooba248

cross-modal-retriever

tooba248/cross-modal-retriever

cross-modal-retriever is a machine learning model from tooba248. Use it for the machine learning task on the model card, and read the license before you ship it in a product.

This app evaluates a fine-tuned CLIP model using the full test split from Flickr30k. - Upload an image to retrieve its best-matching caption. - Enter a caption to retrieve the closest image.