app.py

import numpy as np
from PIL import Image
import streamlit as st
from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel 

# Directory path to the saved model on Google Drive
model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning

def generate_captions(image):
    image = Image.open(image).convert("RGB")
    generated_caption = tokenizer.decode(model.generate(feature_extractor(image, return_tensors="pt").pixel_values.to("cpu"))[0])
    sentence = generated_caption
    text_to_remove = "<|endoftext|>"
    generated_caption = sentence.replace(text_to_remove, "")
    return generated_caption

# create the Streamlit app
def app():
    st.title('Image from your Side, Trending Hashtags from our Side')

    st.write('Upload an image to see what we have in store.')

    # create file uploader
    uploaded_file = st.file_uploader("Got You Covered, Upload your wish!, magic on the Way! ", type=["jpg", "jpeg", "png"])

    # check if file has been uploaded
    if uploaded_file is not None:
        # load the image
        image = Image.open(uploaded_file).convert("RGB")

        # Image Captions
        string = generate_captions(uploaded_file)

        st.image(image, caption='The Uploaded File')
        st.write("First is first captions for your Photo : ", string)

# run the app
if __name__ == '__main__':
    app()