import torch import torchvision import torchvision.transforms as transforms import torch.nn as nn import torch.optim as optim import matplotlib.pyplot as plt

Load CIFAR-10 dataset

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

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=2)

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=2)

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

Define CNN network

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()

Define loss function and optimizer

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

Train the network

num_epochs = 10 train_loss_history = [] val_loss_history = [] train_acc_history = [] val_acc_history = []

for epoch in range(num_epochs): running_loss = 0.0 train_correct = 0 train_total = 0

for i, data in enumerate(trainloader, 0):
    # Get the inputs
    inputs, labels = data

    # Zero the parameter gradients
    optimizer.zero_grad()

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

    # Compute training accuracy
    _, predicted = torch.max(outputs.data, 1)
    train_total += labels.size(0)
    train_correct += (predicted == labels).sum().item()

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

train_loss_history.append(running_loss / len(trainloader))
train_acc_history.append(train_correct / train_total)

# Validate the network
val_loss = 0.0
val_correct = 0
val_total = 0

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

val_loss_history.append(val_loss / len(testloader))
val_acc_history.append(val_correct / val_total)

Plot losses

plt.plot(train_loss_history, label='Training loss') plt.plot(val_loss_history, label='Validation loss') plt.xlabel('Epoch') plt.ylabel('Loss') plt.legend() plt.show()

Plot accuracies

plt.plot(train_acc_history, label='Training accuracy') plt.plot(val_acc_history, label='Validation accuracy') plt.xlabel('Epoch') plt.ylabel('Accuracy') plt.legend() plt.show()

Print accuracy

print('Accuracy of the network on the 10000 test images: %.2f %%' % (100 * val_correct / val_total))

Testing accuracy

test_correct = 0 test_total = 0

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

print('Accuracy of the network on the 10000 test images: %.2f %%' % (100 * test_correct / test_total))