PyTorch DNN实现MNIST手写数字识别

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms

batch_size = 200
learning_rate = 0.01
epochs = 10

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=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('./data', train=False, download=True,
                   transform=transforms.Compose([transforms.ToTensor(),
                                                 transforms.Normalize((0.1307), (
                                                     0.3081))])),
    batch_size=batch_size, shuffle=True)


class MLP(nn.Module):

    def __init__(self):
        super(MLP, self).__init__()

        self.model = nn.Sequential(
            nn.Linear(784, 200),
            nn.LeakyReLU(inplace=True),
            nn.Linear(200, 200),
            nn.LeakyReLU(inplace=True),
            nn.Linear(200, 10),
            nn.LeakyReLU(inplace=True)
        )

    def forward(self, x):
        x = self.model(x)
        return x


net = MLP()
optimizer = optim.Adam(net.parameters(), lr=learning_rate)
criteon = nn.CrossEntropyLoss()

for epoch in range(epochs):

    for batch_idx, (data, target) in enumerate(train_loader):
        data = data.view(-1, 28 * 28)
        data, target = data, target

        logits = net(data)
        loss = criteon(logits, target)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch_idx % 100 == 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()))

    test_loss = 0
    correct = 0
    for data, target in test_loader:
        data = data.view(-1, 28 * 28)
        logits = net(data)
        test_loss += criteon(logits, target).item()

        pred = logits.data.max(1)[1]
        correct += pred.eq(target.data).sum()

    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)))

用SGD时收敛速度，准确率明显比Adam慢，低

GPU版本

import torch
import torch.nn as nn
import torch.optim as optim
from torchvision import datasets, transforms

batch_size = 200
learning_rate = 0.01
epochs = 10
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

train_loader = torch.utils.data.DataLoader(
    datasets.MNIST('./mnist_data', train=True, download=True,
                   transform=transforms.Compose([transforms.ToTensor(),
                                                 transforms.Normalize((0.1307), (
                                                     0.3081))])),
    batch_size=batch_size, shuffle=True)
test_loader = torch.utils.data.DataLoader(
    datasets.MNIST('./mnist_data', train=False, download=True,
                   transform=transforms.Compose([transforms.ToTensor(),
                                                 transforms.Normalize((0.1307), (
                                                     0.3081))])),
    batch_size=batch_size, shuffle=True)


class MLP(nn.Module):

    def __init__(self):
        super(MLP, self).__init__()

        self.model = nn.Sequential(
            nn.Linear(784, 200),
            nn.LeakyReLU(inplace=True),
            nn.Linear(200, 200),
            nn.LeakyReLU(inplace=True),
            nn.Linear(200, 10),
            nn.LeakyReLU(inplace=True)
        )

    def forward(self, x):
        x = self.model(x)
        return x


net = MLP().to(device)
optimizer = optim.Adam(net.parameters(), lr=learning_rate)
criteon = nn.CrossEntropyLoss()

for epoch in range(epochs):

    for batch_idx, (data, target) in enumerate(train_loader):
        data = data.view(-1, 28 * 28)
        data, target = data.to(device), target.to(device)

        logits = net(data)
        loss = criteon(logits, target)

        optimizer.zero_grad()
        loss.backward()
        optimizer.step()

        if batch_idx % 100 == 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()))

    test_loss = 0
    correct = 0
    for data, target in test_loader:
        data = data.view(-1, 28 * 28)
        data, target = data.to(device), target.to(device)
        logits = net(data)
        test_loss += criteon(logits, target).item()

        pred = logits.data.max(1)[1]
        correct += pred.eq(target.data).sum()

    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)))

因为网络规模太小，GPU由于数据传输慢于CPU，所以反而比CPU慢