Torch.hub.load custom model

isaacnewton35 · April 11, 2021, 12:38pm

RuntimeError: Attempting to deserialize object on a CUDA device but torch.cuda.is_available() is False. If you are running on a CPU-only machine, please use torch.load with map_location=torch.device(‘cpu’) to map your storages to the CPU.

Traceback:

ım getting this error while making yolo webapp
here is my code

github.com

yupopa/yolov5/blob/main/ncc.py

import streamlit as st
import requests
import base64
import io
from PIL import Image
import glob
from base64 import decodebytes
from io import BytesIO
import numpy
import matplotlib.pyplot as plt
import torch
from urllib.request import urlretrieve
from fastai.vision.widgets import *
from fastai.vision.all import *
import cv2
from contextlib import contextmanager, redirect_stdout
from io import StringIO
from time import sleep
import streamlit as st

This file has been truncated. show original

Franky1 · April 11, 2021, 9:47pm

The error message actually gives a clear indication of what the problem might be, doesn’t it?

Topic		Replies	Views
Yolov5 error 🎈 Using Streamlit	2	1072	May 13, 2022
I am getting an error while deploying my app on streamlit 🚀 Deployment discussion	5	216	March 15, 2024
ModuleNotFoundError: No module named 'torch' 🎈 Using Streamlit	1	982	June 21, 2023
Unable to load model weights error 🚀 Deployment pytorch	3	3291	July 26, 2021
Pls help me appreciated github id（https://github.com/AbdukeramDolkun/detectstuff/tree/main/YOLOv8-streamlit-app-master） 🎈 Using Streamlit opencv	5	259	December 15, 2023

Torch.hub.load custom model

Related Topics

Hello there 👋🏻

Cookie settings

Strictly necessary cookies

Performance cookies

Functional cookies

Targeting cookies