GPU performance issues of flask framework

[hky3535]

When I loaded an ultralytics YOLO model outside the framework, I read the image from the client in a request processing function and performed inference. I found that the inference speed was 10 times slower than normal.
I don’t have this problem when I use fastapi.

from flask import Flask, request

from ultralytics import YOLO
import cv2
import numpy
import base64
model = YOLO("/workspace/yolov8s.pt")
def b64_cv(frame_b64):
    return cv2.imdecode(numpy.frombuffer(base64.b64decode(frame_b64), numpy.uint8), cv2.IMREAD_COLOR)

app = Flask(__name__)

@app.route('/frame', methods=['POST'])
def read_item():
    data = request.json
    frame = data.get('frame', None)
    
    results = model(source=b64_cv(frame))

    return {}

if __name__ == '__main__':
    app.run(host='0.0.0.0', port=8000)

import requests
import cv2
import numpy
import base64

def cv_b64(frame_cv):
    return str(base64.b64encode(cv2.imencode(".jpg", frame_cv)[1]))[2:-1]

while True:
    stream = cv2.VideoCapture("/workspace/road_30_1920x1080.mp4")
    while stream.isOpened():
        ret, frame = stream.read()
        if not ret: break

        data = {"frame": cv_b64(frame)}
        response = requests.post(url="http://127.0.0.1:8000/frame", json=data)

Environment:

• Python version: 3.10.12
• Flask version: 3.0.0