app.py

import cv2
import numpy as np
import gradio as gr

net = cv2.dnn.readNetFromCaffe(
    "MobileNetSSD_deploy.prototxt", "MobileNetSSD_deploy.caffemodel"
)

class_names = [
    "background",
    "aeroplane",
    "bicycle",
    "bird",
    "boat",
    "bottle",
    "bus",
    "car",
    "cat",
    "chair",
    "cow",
    "diningtable",
    "dog",
    "horse",
    "motorbike",
    "person",
    "pottedplant",
    "sheep",
    "sofa",
    "train",
    "tvmonitor",
]


def detect_objects(image):
    frame = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)
    blob = cv2.dnn.blobFromImage(
        frame, 0.007843, (300, 300), (127.5, 127.5, 127.5), swapRB=False, crop=False
    )
    net.setInput(blob)
    detections = net.forward()

    for i in range(detections.shape[2]):
        confidence = detections[0, 0, i, 2]
        if confidence > 0.2:
            idx = int(detections[0, 0, i, 1])
            box = detections[0, 0, i, 3:7] * np.array(
                [frame.shape[1], frame.shape[0], frame.shape[1], frame.shape[0]]
            )
            (startX, startY, endX, endY) = box.astype("int")

            label = f"{class_names[idx]}: {confidence:.2f}"
            cv2.rectangle(frame, (startX, startY), (endX, endY), (0, 255, 0), 2)
            y = startY - 15 if startY - 15 > 15 else startY + 15
            cv2.putText(
                frame,
                label,
                (startX, y),
                cv2.FONT_HERSHEY_SIMPLEX,
                0.5,
                (255, 255, 255),
                2,
            )

    return cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)


iface = gr.Interface(fn=detect_objects, inputs="image", outputs="image", live=True)
iface.launch()