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/yolov10n", filename="onnx/model.onnx" ) model = YOLOv10(model_file) account_sid = os.environ.get("TWILIO_ACCOUNT_SID") auth_token = os.environ.get("TWILIO_AUTH_TOKEN") if account_sid and auth_token: client = Client(account_sid, auth_token) token = client.tokens.create() rtc_configuration = { "iceServers": token.ice_servers, "iceTransportPolicy": "relay", } else: rtc_configuration = None 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 cv2.resize(new_image, (500, 500)) 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( """

YOLOv10 Webcam Stream (Powered by WebRTC ⚡️)

""" ) gr.HTML( """

arXiv | github

""" ) 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.stream( fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10 ) if __name__ == "__main__": demo.launch()