app.py

import gradio as gr
from transformers import DetrImageProcessor, DetrForObjectDetection
import torch
from PIL import Image, ImageDraw

# Load pre-trained model and processor
processor = DetrImageProcessor.from_pretrained("facebook/detr-resnet-50")
model = DetrForObjectDetection.from_pretrained("facebook/detr-resnet-50")

# Object detection function
def detect_objects(image):
    # Convert image and run model
    inputs = processor(images=image, return_tensors="pt")
    outputs = model(**inputs)

    # Get outputs
    target_sizes = torch.tensor([image.size[::-1]])  # PIL: (W, H) -> expected (H, W)
    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]

    # Draw boxes on the image
    draw = ImageDraw.Draw(image)
    for score, label, box in zip(results["scores"], results["labels"], results["boxes"]):
        box = [round(i, 2) for i in box.tolist()]
        draw.rectangle(box, outline="red", width=3)
        draw.text((box[0], box[1]), f"{model.config.id2label[label.item()]}: {round(score.item(), 3)}", fill="red")

    return image

# Launch Gradio interface
demo = gr.Interface(
    fn=detect_objects,
    inputs=gr.Image(source="camera", tool="editor", live=True),
    outputs=gr.Image(type="pil"),
    title="Real-Time Object Detection",
    description="Open webcam and detect objects using facebook/detr-resnet-50"
)

if __name__ == "__main__":
    demo.launch()