1. 背景

上一篇https://blog.csdn.net/wyw0000/article/details/137622977?spm=1001.2014.3001.5502中实现手撸代码的方式实现了手写数字识别，本文将使用pytorch的API实现。

2. nn.Linear线性层

相当于x = x@w1.t() + b1
因此可以使用nn.Linear代替，上一篇文中中的

w1, b1 = torch.randn(200, 784, requires_grad=True),\
         torch.zeros(200, requires_grad=True)
x = x@w1.t() + b1

使用nn.Linear定义的三层网络，如下图所示：

增加激活函数relu

2. 实现MLP网络

• 实现__init__函数
• 将网络各层放到序列化容器Sequential中
  见下图使用nn.Sequential创建一个小的model，运行时输入首先传给nn.Linear(784, 200)，nn.Linear(784, 200)的输出再传给nn.ReLU(inplace=True)，这样依次传递下去，直至结束。
• 实现forward
  调用将输入x作为model的参数调用model，并将结果返回。
  

3. train

4. 完整代码

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

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)



class MLP(nn.Module):

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

        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),
        )

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

        return x

net = MLP()
optimizer = optim.SGD(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)

        logits = net(data)
        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()))


    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)))