from ultralytics import ASSETS, YOLO, RTDETR
import gradio as gr
from huggingface_hub import snapshot_download
from PIL import Image

model_dir = snapshot_download("omarelsayeed/DETR-ARABIC-DOCUMENT-LAYOUT-ANALYSIS") + "/rtdetr_1024_crops.pt"
model = RTDETR(model_dir)


def predict_image(img, conf_threshold, iou_threshold):
    """Predicts objects in an image using a YOLO11 model with adjustable confidence and IOU thresholds."""
    results = model.predict(
        source=img,
        conf=conf_threshold,
        iou=iou_threshold,
        show_labels=True,
        show_conf=True,
        imgsz=1024,
    )

    for r in results:
        im_array = r.plot()
        im = Image.fromarray(im_array[..., ::-1])

    return im


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"),
    title="Ultralytics Gradio",
    description="Upload images for inference. The Ultralytics YOLO11n model is used by default.",
    examples=[
        ["kashida.png", 0.2, 0.45],
        ["image.jpg", 0.2, 0.45],
        ["Screenshot 2024-11-06 130230.png" , 0.25 , 0.45]
    ],
    theme=gr.themes.Default()
)

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