app.py

import gradio as gr
import cv2
import numpy as np
from gradio_webrtc import WebRTC
from pathlib import Path

CLASSES = [
    "background",
    "aeroplane",
    "bicycle",
    "bird",
    "boat",
    "bottle",
    "bus",
    "car",
    "cat",
    "chair",
    "cow",
    "diningtable",
    "dog",
    "horse",
    "motorbike",
    "person",
    "pottedplant",
    "sheep",
    "sofa",
    "train",
    "tvmonitor",
]
COLORS = np.random.uniform(0, 255, size=(len(CLASSES), 3))

directory = Path(__file__).parent

MODEL = str((directory / "MobileNetSSD_deploy.caffemodel").resolve())
PROTOTXT = str((directory / "MobileNetSSD_deploy.prototxt.txt").resolve())
net = cv2.dnn.readNetFromCaffe(PROTOTXT, MODEL)


def detection(image, conf_threshold=0.3):

    blob = cv2.dnn.blobFromImage(
        cv2.resize(image, (300, 300)), 0.007843, (300, 300), 127.5
    )
    net.setInput(blob)

    detections = net.forward()
    image = cv2.resize(image, (500, 500))
    (h, w) = image.shape[:2]
    labels = []
    for i in np.arange(0, detections.shape[2]):
        confidence = detections[0, 0, i, 2]

        if confidence > conf_threshold:
            # extract the index of the class label from the `detections`,
            # then compute the (x, y)-coordinates of the bounding box for
            # the object
            idx = int(detections[0, 0, i, 1])
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            # display the prediction
            label = f"{CLASSES[idx]}: {round(confidence * 100, 2)}%"
            labels.append(label)
            cv2.rectangle(image, (startX, startY), (endX, endY), COLORS[idx], 2)
            y = startY - 15 if startY - 15 > 15 else startY + 15
            cv2.putText(
                image, label, (startX, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, COLORS[idx], 2
            )
    return image


css=""".my-group {max-width: 600px !important; max-height: 600 !important;}
                      .my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""


with gr.Blocks(css=css) as demo:
    gr.HTML(
        """
    <h1 style='text-align: center'>
    YOLOv10 Webcam Stream
    </h1>
    """)
    gr.HTML(
        """
        <h3 style='text-align: center'>
        <a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
        </h3>
        """)
    with gr.Column(elem_classes=["my-column"]):
        with gr.Group(elem_classes=["my-group"]):
            image = WebRTC(label="Strean")
            conf_threshold = gr.Slider(
                label="Confidence Threshold",
                minimum=0.0,
                maximum=1.0,
                step=0.05,
                value=0.30,
            )
        
        image.webrtc_stream(
            fn=detection,
            inputs=[image],
            stream_every=0.05,
            time_limit=30
        )

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