app.py

import streamlit as st
from transformers import ViTImageProcessor, ViTForImageClassification
from PIL import Image as img

x = st.file_uploader("Upload Images", type=["png","jpg","jpeg"])
if x is not None:
    st.image(img.open(x),width=255)
    i = img.open(x)
    processor = ViTImageProcessor.from_pretrained('google/vit-base-patch16-224')
    model = ViTForImageClassification.from_pretrained('google/vit-base-patch16-224')
    inputs = processor(images=i, return_tensors="pt")
    outputs = model(**inputs)
    logits = outputs.logits
    predicted_class_idx = logits.argmax(-1).item()
    st.text("Our Model Predicts : ")
    st.write(model.config.id2label[predicted_class_idx])