Run CIFAR

cifar10_benchmark.py

#!/usr/bin/env python3
# Results of recent runs:
# Mac Apple M1 50.3 sec
# Mac Intel(R) Core(TM) i9-9980HK CPU @ 2.40GH in 61.1 sec
# Linux Intel(R) Xeon(R) W-2135 CPU @ 3.70GHz in 53.5 sec
import time
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms

def get_cpu_name():
    import platform
    from subprocess import check_output
    if platform.system() == "Darwin":
        return check_output(["sysctl", "-n", "machdep.cpu.brand_string"]).decode("latin").strip()
    if platform.system() == "Linux":
        for line in check_output(["cat", "/proc/cpuinfo"]).decode("latin").split("\n"):
            if "model name" in line:
                return line.split(":",1)[1].strip()
    return platform.processor()


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


def main():
    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)


    net = Net()

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

    start_time = time.time()
    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

            # 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
    end_time = time.time()

    print(f'Finished Training on {get_cpu_name()} in {end_time-start_time:.2f} seconds')

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

if __name__ == '__main__':
    main()