PyTorch TRAINING A CLASSIFIER tutorial error during CUDA run

I am trying to run PyTorch TRAINING A CLASSIFIER tutorial code with CUDA. https://pytorch.org/tutorials/beginner/blitz/cifar10_tutorial.html#sphx-glr-beginner-blitz-cifar10-tutorial-py The code is below. The code runs fine for CPU, but gives the following error with GPU-CUDA run:

"Process finished with exit code -1073741819 (0xC0000005) The error happens during execution of the loss.backward()

I will be very grateful to solution.

import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.optim as optim

# Let’s first define our device as the first visible cuda device if we have CUDA available:

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
# device = torch.device("cpu")

# Assuming that we are on a CUDA machine, this should print a CUDA device:

print(device)
# The output of torchvision datasets are PILImage images of range [0, 1]. We transform them to Tensors of normalized range [-1, 1]. .. note:
#
# If running on Windows and you get a BrokenPipeError, try setting
# the num_worker of torch.utils.data.DataLoader() to 0.

transform = transforms.Compose(
    [transforms.ToTensor(),
     transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

# Use CIFAR10
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
                                        download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4,
                                          shuffle=True, num_workers=0)

testset = torchvision.datasets.CIFAR10(root='./data', train=False,
                                       download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4,
                                         shuffle=False, num_workers=0)

classes1 =trainset.classes
classes =tuple(classes1)
# https://www.w3schools.com/python/python_tuples.asp
# https://www.geeksforgeeks.org/python-convert-a-list-into-a-tuple/
# classes = ('plane', 'car', 'bird', 'cat',
#            'deer', 'dog', 'frog', 'horse', 'ship', 'truck')



# functions to show an image


def imshow(img):
    img = img / 2 + 0.5     # unnormalize. The output of torchvision datasets
    # are PILImage images of range [0, 1]. We transform
    # them to Tensors of normalized range [-1, 1]. ..
    npimg = img.numpy()
    plt.imshow(np.transpose(npimg, (1, 2, 0)))
    plt.show()


# get some random training images
dataiter = iter(trainloader)
images, labels = dataiter.next()

# show images
imshow(torchvision.utils.make_grid(images))
# print labels
print(' '.join('%5s' % classes[labels[j]] for j in range(4))) # Batch size is 4, Therefore we have 4 images.

# Define a Convolutional Neural Network

# Copy the neural network from the Neural Networks section before and modify it to take 3-channel images (instead of 1-channel images as it was defined).
# Important - this is the way to upgrade my BBOB net.

import torch.nn as nn
import torch.nn.functional as F


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x


net = Net()
net.to(device)


# Define a Loss function and optimizer
# Let’s use a Classification Cross-Entropy loss and SGD with momentum.


criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

# Train the network
# This is when things start to get interesting. We simply have to loop over our data iterator, and feed the inputs to the network and optimize.
# zero the parameter gradients
# optimizer.zero_grad()

for epoch in range(2):  # loop over the dataset multiple times

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # get the inputs; data is a list of [inputs, labels]
        inputs, labels = data
        inputs = inputs.to(device)
        labels = labels.to(device)
        # inputs, labels = data[0].to(device), data[1].to(device)
        # zero the parameter gradients
        optimizer.zero_grad()

        # forward + backward + optimize
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # print statistics
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

# Let’s quickly save our trained model:

PATH = './cifar_net.pth'
torch.save(net.state_dict(), PATH)

# Test the network on the test data
dataiter = iter(testloader)
images, labels = dataiter.next()

# print images
imshow(torchvision.utils.make_grid(images))
print('GroundTruth: ', ' '.join('%5s' % classes[labels[j]] for j in range(4)))

# Next, let’s load back in our saved model (note: saving and re-loading the model wasn’t necessary here, we only did it to illustrate how to do so):

net = Net()
net.load_state_dict(torch.load(PATH))

# Okay, now let us see what the neural network thinks these examples above are:
outputs = net(images)

# The outputs are energies for the 10 classes. The higher the energy for a class, the more the network thinks that the image is of the particular class. So, let’s get the index of the highest energy:

_, predicted = torch.max(outputs, 1)

print('Predicted: ', ' '.join('%5s' % classes[predicted[j]]
                              for j in range(4)))

correct = 0
total = 0
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print('Accuracy of the network on the 10000 test images: %d %%' % (100 * correct / total))

# Hmmm, what are the classes that performed well, and the classes that did not perform well:

class_correct = list(0. for i in range(10))
class_total = list(0. for i in range(10))
with torch.no_grad():
    for data in testloader:
        images, labels = data
        outputs = net(images)
        _, predicted = torch.max(outputs, 1)
        c = (predicted == labels).squeeze()
        for i in range(4):
            label = labels[i]
            class_correct[label] += c[i].item()
            class_total[label] += 1


for i in range(10):
    print('Accuracy of %5s : %2d %%' % (
        classes[i], 100 * class_correct[i] / class_total[i]))