app.py

import json
from pathlib import Path
from fastapi import FastAPI
from fastapi.responses import HTMLResponse
from fastrtc import Stream
from huggingface_hub import hf_hub_download
from pydantic import BaseModel, Field
import os
import cv2

from inference import YOLOv10

cur_dir = Path(__file__).parent

model_file = hf_hub_download(
    repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
)

model = YOLOv10(model_file)

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))

stream = Stream(
    handler=detection,
    modality="video",
    mode="send-receive",
    additional_inputs=[gr.Slider(minimum=0, maximum=1, step=0.01, value=0.3)],
    rtc_configuration=None,
    concurrency_limit=None,
)

app = FastAPI()
stream.mount(app)

@app.get("/")
async def serve_index():
    html_content = open(cur_dir / "index.html").read()
    return HTMLResponse(content=html_content)

class InputData(BaseModel):
    webrtc_id: str
    conf_threshold: float = Field(ge=0, le=1)

@app.post("/input_hook")
async def update_input(data: InputData):
    stream.set_input(data.webrtc_id, data.conf_threshold)

if __name__ == "__main__":
    if (mode := os.getenv("MODE")) == "UI":
        stream.ui.launch(server_port=7860)
    elif mode == "PHONE":
        stream.fastphone(host="0.0.0.0", port=7860)
    else:
        import uvicorn
        uvicorn.run(app, host="0.0.0.0", port=7860)