MachineLearningNotebooks/how-to-use-azureml/deployment/onnx/mnist.py

# This is a modified version of https://github.com/pytorch/examples/blob/master/mnist/main.py which is
# licensed under BSD 3-Clause (https://github.com/pytorch/examples/blob/master/LICENSE)

from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import os


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)

    def forward(self, x):
        x = F.relu(F.max_pool2d(self.conv1(x), 2))
        x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))
        x = x.view(-1, 320)
        x = F.relu(self.fc1(x))
        x = F.dropout(x, training=self.training)
        x = self.fc2(x)
        return F.log_softmax(x, dim=1)


def train(args, model, device, train_loader, optimizer, epoch, output_dir):
    model.train()
    for batch_idx, (data, target) in enumerate(train_loader):
        data, target = data.to(device), target.to(device)
        optimizer.zero_grad()
        output = model(data)
        loss = F.nll_loss(output, target)
        loss.backward()
        optimizer.step()
        if batch_idx % args.log_interval == 0:
            print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
                epoch, batch_idx * len(data), len(train_loader.dataset),
                100. * batch_idx / len(train_loader), loss.item()))


def test(args, model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            data, target = data.to(device), target.to(device)
            output = model(data)
            test_loss += F.nll_loss(output, target, size_average=False, reduce=True).item()  # sum up batch loss
            pred = output.max(1, keepdim=True)[1]  # get the index of the max log-probability
            correct += pred.eq(target.view_as(pred)).sum().item()

    test_loss /= len(test_loader.dataset)
    print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
        test_loss, correct, len(test_loader.dataset),
        100. * correct / len(test_loader.dataset)))


def main():
    # Training settings
    parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
    parser.add_argument('--batch-size', type=int, default=64, metavar='N',
                        help='input batch size for training (default: 64)')
    parser.add_argument('--test-batch-size', type=int, default=1000, metavar='N',
                        help='input batch size for testing (default: 1000)')
    parser.add_argument('--epochs', type=int, default=5, metavar='N',
                        help='number of epochs to train (default: 5)')
    parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
                        help='learning rate (default: 0.01)')
    parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
                        help='SGD momentum (default: 0.5)')
    parser.add_argument('--no-cuda', action='store_true', default=False,
                        help='disables CUDA training')
    parser.add_argument('--seed', type=int, default=1, metavar='S',
                        help='random seed (default: 1)')
    parser.add_argument('--log-interval', type=int, default=10, metavar='N',
                        help='how many batches to wait before logging training status')
    parser.add_argument('--output-dir', type=str, default='outputs')
    args = parser.parse_args()
    use_cuda = not args.no_cuda and torch.cuda.is_available()

    torch.manual_seed(args.seed)

    device = torch.device("cuda" if use_cuda else "cpu")

    output_dir = args.output_dir
    os.makedirs(output_dir, exist_ok=True)

    kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
    # Use Azure Open Datasets for MNIST dataset
    datasets.MNIST.resources = [
        ("https://azureopendatastorage.azurefd.net/mnist/train-images-idx3-ubyte.gz",
         "f68b3c2dcbeaaa9fbdd348bbdeb94873"),
        ("https://azureopendatastorage.azurefd.net/mnist/train-labels-idx1-ubyte.gz",
         "d53e105ee54ea40749a09fcbcd1e9432"),
        ("https://azureopendatastorage.azurefd.net/mnist/t10k-images-idx3-ubyte.gz",
         "9fb629c4189551a2d022fa330f9573f3"),
        ("https://azureopendatastorage.azurefd.net/mnist/t10k-labels-idx1-ubyte.gz",
         "ec29112dd5afa0611ce80d1b7f02629c")
    ]
    train_loader = torch.utils.data.DataLoader(
        datasets.MNIST('data', train=True, download=True,
                       transform=transforms.Compose([transforms.ToTensor(),
                                                    transforms.Normalize((0.1307,), (0.3081,))])
                       ),
        batch_size=args.batch_size, shuffle=True, **kwargs)
    test_loader = torch.utils.data.DataLoader(
        datasets.MNIST('data', train=False,
                       transform=transforms.Compose([transforms.ToTensor(),
                                                    transforms.Normalize((0.1307,), (0.3081,))])
                       ),
        batch_size=args.test_batch_size, shuffle=True, **kwargs)

    model = Net().to(device)
    optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)

    for epoch in range(1, args.epochs + 1):
        train(args, model, device, train_loader, optimizer, epoch, output_dir)
        test(args, model, device, test_loader)

    # save model
    dummy_input = torch.randn(1, 1, 28, 28, device=device)
    model_path = os.path.join(output_dir, 'mnist.onnx')
    torch.onnx.export(model, dummy_input, model_path)


if __name__ == '__main__':
    main()