import gradio as gr
import PIL.Image as Image
from ultralytics import ASSETS, YOLO

model = YOLO("yolo12x.pt")

def predict_image(img, conf_threshold, iou_threshold):
    """Predicts persons and cars in an image and returns the image with detections and counts."""
    results = model.predict(
        source=img,
        conf=conf_threshold,
        iou=iou_threshold,
        show_labels=True,
        show_conf=True,
        imgsz=640,
        classes=[0, 2]  # 0 for person, 2 for car
    )
    
    for r in results:
        im_array = r.plot()
        im = Image.fromarray(im_array[..., ::-1])
        
        # Count persons and cars separately
        person_count = 0
        car_count = 0
        
        if results[0].boxes is not None:
            for box in results[0].boxes:
                class_id = int(box.cls[0])
                if class_id == 0:  # person
                    person_count += 1
                elif class_id == 2:  # car
                    car_count += 1
        
        total_count = person_count + car_count
        count_text = f"Persons: {person_count} | Cars: {car_count} | Total: {total_count}"
        
    return im, count_text

iface = gr.Interface(
    fn=predict_image,
    inputs=[
        gr.Image(type="pil", label="Upload Image"),
        gr.Slider(minimum=0, maximum=1, value=0.25, label="Confidence threshold"),
        gr.Slider(minimum=0, maximum=1, value=0.45, label="IoU threshold"),
    ],
    outputs=[
        gr.Image(type="pil", label="Result"),
        gr.Textbox(label="Detection Count")
    ],
    title="Person and Car Detection",
    description="Upload images to detect persons and cars with individual counts",
)

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