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

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

# Load labels
labels = model.config.id2label

def detect_objects(image):
    inputs = processor(images=image, return_tensors="pt")
    outputs = model(**inputs)

    target_sizes = torch.tensor([image.size[::-1]])
    results = processor.post_process_object_detection(outputs, target_sizes=target_sizes, threshold=0.9)[0]

    draw = ImageDraw.Draw(image)
    font = ImageFont.load_default()

    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=2)
        draw.text((box[0], box[1] - 10), f"{labels[label.item()]}: {round(score.item(), 2)}", fill="red", font=font)

    return image

gr.Interface(fn=detect_objects, 
             inputs=gr.Image(type="pil"), 
             outputs=gr.Image(type="pil"),
             title="What’s This? - Object Recognition",
             description="Upload an image to detect objects using DETR").launch()