app.py

import gradio as gr
import cv2
from huggingface_hub import hf_hub_download
from gradio_webrtc import WebRTC
from twilio.rest import Client
import os
from inference import YOLOv10

model_file = hf_hub_download(
    repo_id="onnx-community/yolov10s", filename="onnx/model.onnx"
)

model = YOLOv10(model_file)

account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
client = Client(account_sid, auth_token)

token = client.tokens.create()

rtc_configuration = {
    "iceServers": token.ice_servers,
    "iceTransportPolicy": "relay",
}


def detection(image, conf_threshold=0.3):
    image = cv2.resize(image, (model.input_width, model.input_height))
    new_image = model.detect_objects(image, conf_threshold)
    return new_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 (Powered by WebRTC ⚡️)
    </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="Stream", rtc_configuration=rtc_configuration)
            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, conf_threshold], stream_every=0.05, time_limit=30,
            concurrency_limit=10
        )

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