"""
Gradio demo for TypoRef YOLOv8 Historical Document Detector.

This script defines a simple Gradio interface that allows a user to upload
an image of a historical document page.  The interface loads a YOLOv8
object detection model and applies it to the input image, overlaying
bounding boxes around detected ornaments, typography and other decorative
elements.  The resulting annotated image is returned for display in the
browser.

By default the demo uses a small pretrained YOLOv8 model from the
``ultralytics`` repository (``yolov8n``) so that it can run without any
custom weights.  If you have uploaded your own fine‑tuned weights to
Hugging Face (e.g. ``martinbadrous/TypoRef-YOLOv8-Historical-Document-Detection``)
you can replace the ``model_path`` value below with the repository ID
for your model.  The ``ultralytics`` package will automatically load
the model from Hugging Face when given a repo ID.

To launch the demo locally run ``python app.py``.  When running as a
Hugging Face Space this file will be executed automatically.
"""

import gradio as gr
from tensorflow.keras.models import load_model
from tensorflow.keras.preprocessing import image
import numpy as np
from PIL import Image, ImageDraw

# Load your trained Keras model
model = load_model("model.h5")

def detect_objects(img):
    # Preprocess
    img_resized = img.resize((640, 640))
    x = np.array(img_resized) / 255.0
    x = np.expand_dims(x, axis=0)
    
    # Predict
    preds = model.predict(x)
    conf = float(np.max(preds))
    
    # Draw a placeholder box (you can replace with your actual detection logic)
    draw = ImageDraw.Draw(img)
    draw.rectangle([100, 280, 540, 580], outline="red", width=3)
    draw.text((110, 260), f"Prediction conf {conf:.2f}", fill="red")
    return img

demo = gr.Interface(
    fn=detect_objects,
    inputs=gr.Image(type="pil", label="Upload a historical document page"),
    outputs=gr.Image(label="Predicted ornaments / layout regions"),
    title="TypoRef: Historical Document Ornament Detection",
    description="Fine-tuned model (.h5) for detecting typographical ornaments in historical prints."
)

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