app.py

# -*- coding: utf-8 -*-
"""
Created on Wed Nov 13 18:37:31 2024
@author: sabar
"""

import gradio as gr
import cv2
import numpy as np
import os
import json
from openvino.runtime import Core  # Assuming you're using OpenVINO
from tf_post_processing import non_max_suppression  # Assuming this is defined elsewhere
from PIL import Image

# Load the OpenVINO model
classification_model_xml = "./model/best.xml"
core = Core()
config = {
    "INFERENCE_NUM_THREADS": 2,
    "ENABLE_CPU_PINNING": True
}
model = core.read_model(model=classification_model_xml)
compiled_model = core.compile_model(model=model, device_name="CPU", config=config)

label_to_class_text = {
    0: 'range',
    1: 'entry door',
    2: 'kitchen sink',
    3: 'bathroom sink',
    4: 'toilet',
    5: 'double folding door',
    6: 'window',
    7: 'shower',
    8: 'bathtub',
    9: 'single folding door',
    10: 'dishwasher',
    11: 'refrigerator'
}

# Function to perform inference
def predict_image(image):
    # Convert the Pillow image to a NumPy array and BGR format for OpenCV
    image = np.array(image.convert("RGB"))
    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
    
    # Resize, preprocess, and reshape the input image
    img_size = 960
    resized_image = cv2.resize(image, (img_size, img_size)) / 255.0
    resized_image = resized_image.transpose(2, 0, 1)
    reshaped_image = np.expand_dims(resized_image, axis=0).astype(np.float32)
    
    im_height, im_width, _ = image.shape
    output_numpy = compiled_model(reshaped_image)[0]
    results = non_max_suppression(output_numpy, conf_thres=0.2, iou_thres=0.6, max_wh=15000)[0]

    # Prepare output paths
    output_path = "./output_file_train/"
    output_image_folder = os.path.join(output_path, "images_alienware_openvino/")
    os.makedirs(output_image_folder, exist_ok=True)

    output_json_folder = os.path.join(output_path, "json_output/")
    os.makedirs(output_json_folder, exist_ok=True)
    
    predictions = []

    # Draw boxes and collect prediction data
    for result in results:
        boxes = result[:4]
        prob = result[4]
        classes = int(result[5])

        x1, y1, x2, y2 = np.uint16([
            boxes[0] * im_width,
            boxes[1] * im_height,
            boxes[2] * im_width,
            boxes[3] * im_height
        ])

        if prob > 0.2:
            cv2.rectangle(image, (x1, y1), (x2, y2), (255, 255, 0), 2)
            label_text = f"{classes} {round(prob, 2)}"
            cv2.putText(image, label_text, (x1, y1), 0, 0.5, (0, 255, 0), 2)

            # Store prediction info in a JSON-compatible format
            predictions.append({
                "class": label_to_class_text[classes],
                "probability": round(float(prob), 2),
                "coordinates": {
                    "xmin": int(x1),
                    "ymin": int(y1),
                    "xmax": int(x2),
                    "ymax": int(y2)
                }
            })

    # Save the processed image
    output_image_path = os.path.join(output_image_folder, "result_image.jpg")
    cv2.imwrite(output_image_path, image)

    # Convert predictions to a formatted string
    predictions_str = json.dumps(predictions, indent=4)

    return image, predictions_str

# Define sample images for user convenience
sample_images = [
    "./sample/10_2.jpg",
    "./sample/10_10.jpg",
    "./sample/10_12.jpg"
]

# Set up Gradio interface
def gradio_interface(image):
    output_image, predictions_str = predict_image(image)
    return output_image, predictions_str

# Create the Gradio Interface
gr_interface = gr.Interface(
    fn=gradio_interface,
    inputs=gr.Image(label="Upload or Select an Image", type="pil", examples=sample_images),
    outputs=[gr.Image(label="Result Image"), gr.Textbox(label="Predictions JSON")],
    title="House CAD Design Object Detection",
    description="Upload a CAD design image of a house to detect objects with bounding boxes and probabilities."
)

# Launch the Gradio interface if run as main
if __name__ == "__main__":
    gr_interface.launch()