I’m trying to run the VGG16 pre-trained model on GPU using Pytorch on Linux Mint. This code snippet

import torch
import torch.nn as nn
import torchvision.transforms as transforms
from PIL import Image
import torchvision.models as models
import time
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
print( device)
vgg16 = models.vgg16(pretrained=True).cuda()

prints cpu and throws error

RuntimeError: No CUDA GPUs are available

Tp solve the issue, I tun the following command in terminal

nvcc --version

and the output is

nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2021 NVIDIA Corporation
Built on Thu_Nov_18_09:45:30_PST_2021
Cuda compilation tools, release 11.5, V11.5.119
Build cuda_11.5.r11.5/compiler.30672275_0

Since the version is 11.5.119, I installed this

pip install torch torchvision torchaudio -f https://download.pytorch.org/whl/cu11.5.119/torch_stable.html

But the error still persists. How can I solve the issue?