app.py

#import all necessary libraries
import torch
import numpy as np
from PIL import Image
import streamlit as st
from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel, BartTokenizer, BartForConditionalGeneration

# pre-trained model to arrive at context
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")

# pre-trained to arrive at description
tokenizer_2 = BartTokenizer.from_pretrained("facebook/bart-large-cnn")
model_2 = BartForConditionalGeneration.from_pretrained("facebook/bart-large-cnn")

# function to generate context
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

# function to generate description
def generate_paragraph(caption):
    # Tokenize the caption
    inputs = tokenizer_2([caption], max_length=1024, truncation=True, padding="longest", return_tensors="pt")

    # Generate text
    output = model_2.generate(inputs.input_ids, attention_mask=inputs.attention_mask, max_length=200, num_beams=4, length_penalty=2.0, early_stopping=True)

    # Decode the generated output
    generated_text = tokenizer_2.decode(output[0], skip_special_tokens=True)
    return generated_text.capitalize()

# create the Streamlit app
def app():
    st.title('Image from your Side, Detailed description from my site')

    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')
        generated_paragraph = generate_paragraph(string)

        st.write(generated_paragraph)
# run the app
if __name__ == '__main__':
    app()