app.py

from transformers import ViltProcessor, ViltForQuestionAnswering
from PIL import Image
import streamlit as st

x = st.file_uploader("Upload Images", type=["png","jpg","jpeg"])
if x is not None:
    st.image(Image.open(x), width=250)
    i = Image.open(x)
    question = st.text_input("Enter your question about the image ? ")
    processor = ViltProcessor.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
    model = ViltForQuestionAnswering.from_pretrained("dandelin/vilt-b32-finetuned-vqa")
    encoding = processor(i, question, return_tensors="pt")
    outputs = model(**encoding)
    logits = outputs.logits
    idx = logits.argmax(-1).item()
    st.write("Model replay:", model.config.id2label[idx])