app.py

import streamlit as st
from transformers import DetrImageProcessor, DetrForObjectDetection, pipeline
import torch
from PIL import Image

# Load the DETR model for object detection
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50", revision="no_timm")
detr_model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50", revision="no_timm")

# Load an NLP model for summarization (T5-small used as an example)
summarizer = pipeline("summarization", model="t5-small")

st.title("Hassan's Project")
st.title("Object Detection with a Summary")
st.write("Upload an image to detect objects and get a summary of what is detected.")

# File uploader in Streamlit
uploaded_file = st.file_uploader("Choose an image...", type="jpg")

if uploaded_file is not None:
    # Load and display the image
    image = Image.open(uploaded_file)
    st.image(image, caption='Uploaded Image', use_column_width=True)

    # Process the image and perform object detection
    inputs = processor(images=image, return_tensors="pt")
    outputs = detr_model(**inputs)

    # Post-process the results to get bounding boxes and labels with a lower confidence threshold
    target_sizes = torch.tensor([image.size[::-1]])
    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.5)[0]

    # Generate descriptions for detected objects
    descriptions = []
    st.write("Detected objects:")
    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
        box = [round(i, 2) for i in box.tolist()]
        label_text = detr_model.config.id2label[label.item()]
        description = f"Detected {label_text} with confidence {round(score.item(), 2)} at location {box}."
        descriptions.append(description)
        st.write(description)  # Display each detected object

    # Combine descriptions into a single text input for the summarizer
    description_text = " ".join(descriptions)

    # Generate a summary using the NLP model
    summary = summarizer(description_text, max_length=50, min_length=10, do_sample=False)[0]['summary_text']
    
    # Display the summary
    st.subheader("Summary")
    st.write(summary)