This repository contains code for generating captions for images using a Transformer-based model. The model used is the `VisionEncoderDecoderModel` from the Hugging Face Transformers library, specifically the `nlpconnect/vit-gpt2-image-captioning` model.
We need to deploy this project cause, it says
transfromers
are not found while deploying in streamlit app !!P.l Refer to https://sap-photo-cap.streamlit.app/