app.py

import os
import cv2
import random
import matplotlib.pyplot as plt
from ultralytics import YOLO
import gradio as gr

# Load the trained YOLO model
MODEL_PATH = "best.pt"  # Replace with your model's path
model = YOLO(MODEL_PATH)

def random_color():
    """Generate a random color for bounding boxes."""
    return (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255))

def detect_and_visualize(image_path):
    """
    Perform object detection and visualize the results.

    Args:
        image_path (str): Path to the input image.

    Returns:
        Annotated image as an array.
        Detection details as a dictionary.
    """
    # Perform object detection
    results = model(image_path)

    # Read the input image
    image = cv2.imread(image_path)
    image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)  # Convert to RGB

    detections = []
    for result in results:
        boxes = result.boxes.xyxy.cpu().numpy()  # Bounding box coordinates
        confidences = result.boxes.conf.cpu().numpy()  # Confidence scores
        class_ids = result.boxes.cls.cpu().numpy().astype(int)  # Class IDs

        for box, confidence, class_id in zip(boxes, confidences, class_ids):
            x_min, y_min, x_max, y_max = map(int, box)
            class_name = model.names[class_id]

            # Draw bounding box and label
            color = random_color()
            cv2.rectangle(image, (x_min, y_min), (x_max, y_max), color, 2)
            label = f"{class_name} {confidence:.2f}"
            cv2.putText(image, label, (x_min, y_min - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)

            # Append detection details
            detections.append({
                "label": class_name,
                "confidence": float(confidence),
                "bounding_box": {
                    "x1": x_min,
                    "y1": y_min,
                    "x2": x_max,
                    "y2": y_max
                }
            })

    # Optionally save the annotated image
    output_path = "output/annotated_image.jpg"
    os.makedirs(os.path.dirname(output_path), exist_ok=True)
    cv2.imwrite(output_path, cv2.cvtColor(image, cv2.COLOR_RGB2BGR))
    print(f"Annotated image saved to {output_path}")

    return cv2.cvtColor(image, cv2.COLOR_RGB2BGR), detections

# Gradio interface
def gradio_interface(image):
    """
    Gradio-compatible wrapper for object detection.

    Args:
        image (numpy.array): Input image.

    Returns:
        Annotated image and detection details.
    """
    temp_input_path = "temp_input.jpg"
    cv2.imwrite(temp_input_path, cv2.cvtColor(image, cv2.COLOR_RGB2BGR))  # Save temp file for YOLO
    annotated_image, detections = detect_and_visualize(temp_input_path)
    os.remove(temp_input_path)  # Clean up temp file
    return annotated_image, detections

# Define Gradio interface
interface = gr.Interface(
    fn=gradio_interface,
    inputs=gr.Image(type="numpy", label="Upload Image"),
    outputs=[
        gr.Image(type="numpy", label="Annotated Image"),
        gr.JSON(label="Detection Details")
    ],
    title="YOLO Object Detection",
    description="Upload an image to detect objects and view annotated results along with detailed detection data."
)

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