多分类问题（mnist数据集）

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

batch_size = 64
transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize(mean=[0.1307], std=[0.3081])
])

train_dataset = datasets.MNIST(root='./data',
                               train = True,
                               download=True,
                               transform=transform)
train_loader = DataLoader(train_dataset,
                          shuffle=True,
                          batch_size=batch_size)
test_dataset = datasets.MNIST(root='./data',
                               train = False,
                               download=True,
                               transform=transform)
test_loader = DataLoader(test_dataset,
                          shuffle=False,
                          batch_size=batch_size)

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.l1 = torch.nn.Linear(784, 512)
        self.l2 = torch.nn.Linear(512, 256)
        self.l3 = torch.nn.Linear(256, 128)
        self.l4 = torch.nn.Linear(128, 64)
        self.l5 = torch.nn.Linear(64, 10)

    def forward(self, x):
        x = x.view(-1, 784)
        x = F.relu(self.l1(x))
        x = F.relu(self.l2(x))
        x = F.relu(self.l3(x))
        x = F.relu(self.l4(x))
        return self.l5(x)
model = Net()

criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        optimizer.zero_grad()

        # forward + backward + update
        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch + 1, batch_idx + 1, running_loss / 300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('Accuracy on test set: %d %%' % (100 * correct / total))

if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

输出结果：

[1,   300] loss: 2.195
[1,   600] loss: 0.834
[1,   900] loss: 0.421
Accuracy on test set: 90 %
[2,   300] loss: 0.312
[2,   600] loss: 0.266
[2,   900] loss: 0.233
Accuracy on test set: 94 %
[3,   300] loss: 0.193
[3,   600] loss: 0.165
[3,   900] loss: 0.151
Accuracy on test set: 95 %
[4,   300] loss: 0.129
[4,   600] loss: 0.124
[4,   900] loss: 0.112
Accuracy on test set: 96 %
[5,   300] loss: 0.096
[5,   600] loss: 0.091
[5,   900] loss: 0.092
Accuracy on test set: 96 %
[6,   300] loss: 0.075
[6,   600] loss: 0.075
[6,   900] loss: 0.073
Accuracy on test set: 97 %
[7,   300] loss: 0.055
[7,   600] loss: 0.064
[7,   900] loss: 0.058
Accuracy on test set: 96 %
[8,   300] loss: 0.044
[8,   600] loss: 0.049
[8,   900] loss: 0.052
Accuracy on test set: 97 %
[9,   300] loss: 0.038
[9,   600] loss: 0.039
[9,   900] loss: 0.041
Accuracy on test set: 97 %
[10,   300] loss: 0.029
[10,   600] loss: 0.030
[10,   900] loss: 0.035
Accuracy on test set: 97 %