distributed_training/train_code/pytorch_mnist.py [33:100]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class CUDANotFoundException(Exception):
    pass


def train(args, model, device, train_loader, optimizer, epoch):
    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 and args.rank == 0:
            print(
                "Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}".format(
                    epoch,
                    batch_idx * len(data) * args.world_size,
                    len(train_loader.dataset),
                    100.0 * batch_idx / len(train_loader),
                    loss.item(),
                )
            )
        if args.verbose:
            print("Batch", batch_idx, "from rank", args.rank)


def test(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, reduction="sum").item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # 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), 100.0 * 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,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



distributed_training/train_code/pytorch_mnist_smdp.py [47:115]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
class CUDANotFoundException(Exception):
    pass



def train(args, model, device, train_loader, optimizer, epoch):
    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 and args.rank == 0:
            print(
                "Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}".format(
                    epoch,
                    batch_idx * len(data) * args.world_size,
                    len(train_loader.dataset),
                    100.0 * batch_idx / len(train_loader),
                    loss.item(),
                )
            )
        if args.verbose:
            print("Batch", batch_idx, "from rank", args.rank)


def test(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, reduction="sum").item()  # sum up batch loss
            pred = output.argmax(dim=1, keepdim=True)  # 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), 100.0 * 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,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -