gen_mnist_onnx.py

#!/usr/bin/env python3

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
from torch.optim.lr_scheduler import StepLR

TAKE_IMAGE_FROM_TEST_SET_AND_EXIT = False

# Use False to indicate load model from disk
TRAIN_MODEL = True


class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(14 * 14, 128)
        self.fc2 = nn.Linear(128, 10)

    def forward(self, x):
        x = F.max_pool2d(x, 2)
        x = x.reshape(-1, 1 * 14 * 14)
        x = self.fc1(x)
        x = F.relu(x)
        x = self.fc2(x)
        output = F.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(
                "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(model, device, test_loader):
    model.eval()
    test_loss = 0
    correct = 0
    with torch.no_grad():
        for data, target in test_loader:
            if TAKE_IMAGE_FROM_TEST_SET_AND_EXIT:
                ############################## Take one image from test set ######################################
                from matplotlib import pyplot as plt

                img_np = data[0].numpy()
                img = img_np.ravel().tolist()

                # Print as C++ array literals:
                print("{" + ",".join(list(map(lambda x: str(x) + "f", img))) + "}")
                plt.imshow(img_np[0], interpolation="nearest")
                plt.show()
                exit(0)
                ############################## Take one image from test set ######################################
            data, target = data.to(device), target.to(device)
            output = model(data)
            # print(output[1])
            # exit(0)
            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,
        default=14,
        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(
        "--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(
        "--save-model",
        action="store_true",
        default=False,
        help="For Saving the current Model",
    )
    parser.add_argument(
        "--export-onnx",
        action="store_true",
        default=False,
        help="For exporting models to onnx protobuf.",
    )
    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().to(device)
    optimizer = optim.Adadelta(model.parameters(), lr=args.lr)

    if TRAIN_MODEL:
        scheduler = StepLR(optimizer, step_size=1, gamma=args.gamma)
        for epoch in range(1, args.epochs + 1):
            train(args, model, device, train_loader, optimizer, epoch)
            test(model, device, test_loader)
            scheduler.step()
    else:
        model.load_state_dict(torch.load("mnist_cnn.pt"))
        test(model, device, test_loader)

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

    if args.export_onnx:
        input_names = ["image"]
        output_names = ["prediction"]
        dummy_input = torch.randn(1, 1, 28, 28)
        torch.onnx.export(
            model,
            dummy_input,
            "mnist.onnx",
            verbose=True,
            input_names=input_names,
            output_names=output_names,
        )


if __name__ == "__main__":
    main()