MachineLearningNotebooks/tutorials/get-started-day1/code/pytorch-cifar10-train-with-logging/train.py

import torch
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms

from model import Net
from azureml.core import Run


# ADDITIONAL CODE: get AML run from the current context
run = Run.get_context()

# download CIFAR 10 data
trainset = torchvision.datasets.CIFAR10(
    root='./data',
    train=True,
    download=True,
    transform=torchvision.transforms.ToTensor()
)
trainloader = torch.utils.data.DataLoader(
    trainset,
    batch_size=4,
    shuffle=True,
    num_workers=2
)

if __name__ == "__main__":

    # define convolutional network
    net = Net()

    # set up pytorch loss /  optimizer
    criterion = torch.nn.CrossEntropyLoss()
    optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)

    # train the network
    for epoch in range(2):

        running_loss = 0.0
        for i, data in enumerate(trainloader, 0):
            # unpack the data
            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:
                loss = running_loss / 2000
                # ADDITIONAL CODE: log loss metric to AML
                run.log('loss', loss)
                print(f'epoch={epoch + 1}, batch={i + 1:5}: loss {loss:.2f}')
                running_loss = 0.0

    print('Finished Training')