main.py

import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
from tqdm import tqdm

# ================================================================ #
#                   Load and normalize the data                    #
# ================================================================ #

transform = transforms.Compose([
    transforms.Pad(4),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

# ================================================================ #
#                     Hyper Parameters and Device                  #
# ================================================================ #

batch_size = 32
epochs = 5
learning_rate = 0.001
momentum = 0.9
num_classes = 10

device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')

train_data = torchvision.datasets.CIFAR10(
    root='data',
    train=True,
    download=True,
    transform=transform
)

test_data = torchvision.datasets.CIFAR10(
    root='data',
    train=False,
    download=True,
    transform=transform
)

train_loader = torch.utils.data.DataLoader(
    dataset=train_data,
    batch_size=batch_size,
    shuffle=True
)

test_loader = torch.utils.data.DataLoader(
    dataset=test_data,
    batch_size=batch_size,
    shuffle=False
)

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


def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=(3, 3), stride=stride, padding=(1, 1), bias=False)


def conv1x1(in_planes, out_planes, stride=1):
    """1x1 convolution"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=(1, 1), stride=stride, bias=False)


class BasicBlock(nn.Module):
    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        out = self.relu(out)

        return out


class ResNet(nn.Module):

    def __init__(self, block, layers, num_classes=1000):
        super(ResNet, self).__init__()

        self.in_planes = 64

        self.conv1 = conv3x3(3, self.in_planes)
        self.bn = nn.BatchNorm2d(self.in_planes)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)

        self.layer1 = self.make_layer(block, 64, layers[0])
        self.layer2 = self.make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self.make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self.make_layer(block, 512, layers[3], stride=2)

        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
        self.fc = nn.Linear(512, num_classes)

    def make_layer(self, block, planes, blocks, stride=1):
        downsample = None
        if stride != 1 or self.in_planes != planes:
            downsample = nn.Sequential(
                conv1x1(self.in_planes, planes, stride),
                nn.BatchNorm2d(planes)
            )

        layers = []
        layers.append(block(self.in_planes, planes, stride, downsample))
        self.in_planes = planes
        for _ in range(1, blocks):
            layers.append(block(self.in_planes, planes))

        return nn.Sequential(*layers)

    def forward(self, x):
        x = self.conv1(x)
        x = self.bn(x)
        x = self.relu(x)
        x = self.maxpool(x)

        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)

        x = self.avgpool(x)
        x = torch.flatten(x, 1)
        x = self.fc(x)

        return x


net = ResNet(BasicBlock, [2, 2, 2, 2]).to(device)

# ================================================================ #
#                     Optimizer and Loss function                  #
# ================================================================ #

criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.SGD(net.parameters(), lr=learning_rate, momentum=momentum)

# ================================================================ #
#                      Train and Test the Model                    #
# ================================================================ #
for epoch in range(epochs):
    progress_bar = tqdm(train_loader, nrows=len(train_loader))
    for i, (images, labels) in enumerate(progress_bar):
        inputs, labels = images.to(device), labels.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
    print(f'Epochs: {epoch + 1}/{epochs} Loss: {loss:.4f}')

print('Finished Training')

print('Started Testing')
correct = 0
total = 0

with torch.no_grad():
    for images, labels in tqdm(test_loader, nrows=len(test_loader)):
        images, labels = images.to(device), labels.to(device)
        outputs = net(images)
        _, predicted = torch.max(outputs.data, 1)
        total += labels.size(0)
        correct += (predicted == labels).sum().item()

print(f'Accuracy of the network on test data: {100 * correct / total}')