pytorch/.ci/pytorch/smoke_test/max_autotune.py

import argparse

from torchvision import datasets, transforms

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.optim.lr_scheduler import StepLR


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()  # noqa: UP008
        self.conv1 = nn.Conv2d(1, 32, 3, 1)
        self.conv2 = nn.Conv2d(32, 64, 3, 1)
        self.dropout1 = nn.Dropout(0.25)
        self.dropout2 = nn.Dropout(0.5)
        self.fc1 = nn.Linear(9216, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = self.conv1(x)
        x = F.relu(x)
        x = self.conv2(x)
        x = F.relu(x)
        x = F.max_pool2d(x, 2)
        x = self.dropout1(x)
        x = torch.flatten(x, 1)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.dropout2(x)
        x = self.fc2(x)
        output = F.log_softmax(x, dim=1)
        return output


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:
            print(
                f"Train Epoch: {epoch} "
                f"[{batch_idx * len(data)}/{len(train_loader.dataset)} "
                f"({100.0 * batch_idx / len(train_loader):.0f}%)]\tLoss: {loss.item():.6f}"
            )
            if args.dry_run:
                break


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(
        f"\nTest set: Average loss: {test_loss:.4f}, "
        f"Accuracy: {correct}/{len(test_loader.dataset)} "
        f"({100.0 * correct / len(test_loader.dataset):.0f}%)\n"
    )


def timed(fn):
    start = torch.cuda.Event(enable_timing=True)
    end = torch.cuda.Event(enable_timing=True)
    start.record()
    result = fn()
    end.record()
    torch.cuda.synchronize()
    return result, start.elapsed_time(end) / 1000


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=4,
        metavar="N",
        help="number of epochs to train (default: 14)",
    )
    parser.add_argument(
        "--lr",
        type=float,
        default=1.0,
        metavar="LR",
        help="learning rate (default: 1.0)",
    )
    parser.add_argument(
        "--gamma",
        type=float,
        default=0.7,
        metavar="M",
        help="Learning rate step gamma (default: 0.7)",
    )
    parser.add_argument(
        "--no-cuda", action="store_true", default=False, help="disables CUDA training"
    )
    parser.add_argument(
        "--no-mps",
        action="store_true",
        default=False,
        help="disables macOS GPU training",
    )
    parser.add_argument(
        "--dry-run",
        action="store_true",
        default=False,
        help="quickly check a single pass",
    )
    parser.add_argument(
        "--seed", type=int, default=1, metavar="S", help="random seed (default: 1)"
    )
    parser.add_argument(
        "--log-interval",
        type=int,
        default=100,
        metavar="N",
        help="how many batches to wait before logging training status",
    )
    parser.add_argument(
        "--save-model",
        action="store_true",
        default=False,
        help="For Saving the current Model",
    )
    args = parser.parse_args()
    use_cuda = not args.no_cuda and torch.cuda.is_available()
    use_mps = not args.no_mps and torch.backends.mps.is_available()

    torch.manual_seed(args.seed)
    torch.backends.cuda.matmul.allow_tf32 = True

    if use_cuda:
        device = torch.device("cuda")
    elif use_mps:
        device = torch.device("mps")
    else:
        device = torch.device("cpu")

    train_kwargs = {"batch_size": args.batch_size}
    test_kwargs = {"batch_size": args.test_batch_size}
    if use_cuda:
        cuda_kwargs = {"num_workers": 1, "pin_memory": True, "shuffle": True}
        train_kwargs.update(cuda_kwargs)
        test_kwargs.update(cuda_kwargs)

    transform = transforms.Compose(
        [transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]
    )
    dataset1 = datasets.MNIST("../data", train=True, download=True, transform=transform)
    dataset2 = datasets.MNIST("../data", train=False, transform=transform)
    train_loader = torch.utils.data.DataLoader(dataset1, **train_kwargs)
    test_loader = torch.utils.data.DataLoader(dataset2, **test_kwargs)

    model = Net().to(device)
    opt_model = torch.compile(model, mode="max-autotune")
    optimizer = optim.Adadelta(opt_model.parameters(), lr=args.lr)

    scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
    for epoch in range(1, args.epochs + 1):
        print(
            f"Training Time: {timed(lambda: train(args, opt_model, device, train_loader, optimizer, epoch))[1]}"
        )
        print(
            f"Evaluation Time: {timed(lambda: test(opt_model, device, test_loader))[1]}"
        )
        scheduler.step()

    if args.save_model:
        torch.save(opt_model.state_dict(), "mnist_cnn.pt")


if __name__ == "__main__":
    main()