深度学习pytorch——全连接层（持续更新）

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


batch_size=200
learning_rate=0.01
epochs=10

# 加载数据
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, transform=transforms.Compose([
        transforms.ToTensor(),
        transforms.Normalize((0.1307,), (0.3081,))
    ])),
    batch_size=batch_size, shuffle=True)

#一般采用以下的写法，nn.Linear自带了自己的初始化方式，一般够用，不够的话就要自己写
#注意 nn.ReLU与 F.relu的区别
# 第一步、继承nn.Module,
class MLP(nn.Module):

    def __init__(self):
        super(MLP, self).__init__()
# 第二步、在__init__中初始化layer
        self.model = nn.Sequential(
            nn.Linear(784, 200),
            nn.ReLU(inplace=True),
            nn.Linear(200, 200),
            nn.ReLU(inplace=True),
            nn.Linear(200, 10),
            nn.ReLU(inplace=True),
        )
# 第三步执行forward
    def forward(self, x):
        x = self.model(x)
        return x

net = MLP()
optimizer = optim.SGD(net.parameters(), lr=learning_rate)
criteon = nn.CrossEntropyLoss()
# 训练
for epoch in range(epochs):

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

        logits = net(data) #注意这里是logits
        loss = criteon(logits, target)

        optimizer.zero_grad()
        loss.backward()
        # print(w1.grad.norm(), w2.grad.norm())
        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()))

# 测试
    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)))