模型：

损失函数和优化器：

代码：MNIST手写数字识别

来源：https://blog.csdn.net/qq_39804263/article/details/139685123?fromshare=blogdetail&sharetype=blogdetail&sharerId=139685123&sharerefer=PC&sharesource=m0_63829662&sharefrom=from_link

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

# prepare dataset
batch_size = 64

transform = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, ))
])

train_dataset = datasets.MNIST('data/MNIST/', train=True, transform=transform, download=True)
train_loader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)

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

# design model
class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.linear1 = torch.nn.Linear(784, 512)
        self.linear2 = torch.nn.Linear(512, 256)
        self.linear3 = torch.nn.Linear(256, 128)
        self.linear4 = torch.nn.Linear(128, 64)
        self.linear5 = torch.nn.Linear(64, 10)

    def forward(self, x):
        x = x.view(-1, 784)
        x = F.relu(self.linear1(x))
        x = F.relu(self.linear2(x))
        x = F.relu(self.linear3(x))
        x = F.relu(self.linear4(x))
        x = self.linear5(x) # 不用激活函数，因为 torch.nn.CrossEntropyLoss = softmax + nllloss
        return x
    
model = Net()

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

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

        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

# test
def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            inputs, labels = data
            outputs = model(inputs)
            _, 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)
        if epoch % 10 == 0:
            test()

运行结果：