import argparse

import torch
import torch.optim as optim
from model import Net
from torchvision import datasets, transforms


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 = model.margin_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),
                    100.0 * 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 += model.margin_loss(
                output, target
            ).item()  # sum up batch loss
            pred = (
                output.norm(dim=2).squeeze().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),
            100.0 * correct / len(test_loader.dataset),
        )
    )


def main():
    # Training settings
    parser = argparse.ArgumentParser(description="PyTorch MNIST Example")
    parser.add_argument(
        "--batch-size",
        type=int,
        default=512,
        metavar="N",
        help="input batch size for training (default: 64)",
    )
    parser.add_argument(
        "--test-batch-size",
        type=int,
        default=512,
        metavar="N",
        help="input batch size for testing (default: 1000)",
    )
    parser.add_argument(
        "--epochs",
        type=int,
        default=10,
        metavar="N",
        help="number of epochs to train (default: 10)",
    )
    parser.add_argument(
        "--lr",
        type=float,
        default=0.01,
        metavar="LR",
        help="learning rate (default: 0.01)",
    )
    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",
    )
    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")

    kwargs = {"num_workers": 1, "pin_memory": True} if use_cuda else {}
    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(device=device).to(device)
    optimizer = optim.Adam(model.parameters(), lr=args.lr)

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


if __name__ == "__main__":
    main()