YOLOv5 + ryzen9 5900X = 100% CPU utilization. Why?

Question

Flask

I assembled a PC for this business (neuronka), it cost almost 100t.r.
I think that's it, now it's going to work. But it was not there.
Raised the server on flask:

code from yolov5 documentation

"""
Run a rest API exposing the yolov5s object detection model
"""
import argparse
import io

import torch
from PIL import Image
from flask import Flask, request

app = Flask(__name__)

@app.route('/', methods=["POST"])
def predict():
    if not request.method == "POST":
        return

    if request.files.get("image"):
        image_file = request.files["image"]
        image_bytes = image_file.read()

        img = Image.open(io.BytesIO(image_bytes))

        results = model(img, size=640)  # reduce size=320 for faster inference
        return results.pandas().xyxy[0].to_json(orient="records")


if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Flask API exposing YOLOv5 model")
    parser.add_argument("--port", default=5000, type=int, help="port number")
    args = parser.parse_args()

    model = torch.hub.load("ultralytics/yolov5", "yolov5m", force_reload=True)  # force_reload to recache
    app.run(host="0.0.0.0", port=args.port)  # debug=True causes Restarting with stat

Everything is defined as it should - there are no problems in this regard.
BUT ...... CPU utilization under 100%




How so? After all, this should not be.
Or am I doing something wrong?
Well, I would still understand on some Pentium, but the ryzen9 5900x is one of the top ones.
Where to dig?

Answer 1

It is difficult for me to answer something based on this information, but I have one question. Would you like to try 64-bit python? Emulation of a 32-bit application in any case should eat up the resources of the machine.