多分类问题线性层和训练部分代码的构建

如下图网络是一个十个输出（十分类问题）

首先建立三个线性层

import torch
import torch.nn.functional as F

# 先建立三个线性层 784=>200=>200=>10

w1, b1 = torch.randn(200, 784, requires_grad=True), \
         torch.randn(200, requires_grad=True)
# randn内的参数分别为(ch_out, ch_cn)，784=28*28，适用于常用的mnist数据集
w2, b2 = torch.randn(200, 200, requires_grad=True), \
         torch.randn(200, requires_grad=True)
w3, b3 = torch.randn(10, 200, requires_grad=True), \
         torch.randn(10, requires_grad=True)
# 第二层虽然维度和第一层一样，都是200，但是并不是没有作用，而是经历了特征变换

def forward(x):
    # 经过第一层
    x = x@w1.t() + b1
    x = F.relu(x)
    
    # 经过第二层
    x = x@w2.t() + b2
    x = F.relu(x)
    
    # 经过最后一层
    x = x@w3.t() + b3
    x = F.relu(x)
    
    return x # 这里返回的x没有经过sigmoid和softmax

上面完成了 tensor 和 forward 的建立，下面介绍 train 的部分

# 训练过程首先要建立一个优化器，引入相关工具包
import torch.optim as optim
import torch.nn as nn

lr = 1e-3 # learning_rate

# 优化器优化的目标是三个全连接层的变量
optimizer = optim.SGD([w1, b1, w2, b2, w3, b3], lr=lr)
criteon = nn.CrossEntropyLoss() # 自带softmax,log,CrossEntropy

for epoch in range(epochs):
    for batch_idx, (data, target) in enumerate(train_loader):
        data = data.view(-1, 28*28)
        
        logits = forward(data)
        loss = criteon(logits, target)
        
        optimizer.zero_gradr()
        loss.backward()
        optimizer.step()

这里先要求掌握以上代码的书写，后续需会讲解数据读取、结果验证等其他部分代码

下面给出全部代码

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)



w1, b1 = torch.randn(200, 784, requires_grad=True),\
         torch.zeros(200, requires_grad=True)
w2, b2 = torch.randn(200, 200, requires_grad=True),\
         torch.zeros(200, requires_grad=True)
w3, b3 = torch.randn(10, 200, requires_grad=True),\
         torch.zeros(10, requires_grad=True)

torch.nn.init.kaiming_normal_(w1)
torch.nn.init.kaiming_normal_(w2)
torch.nn.init.kaiming_normal_(w3)


def forward(x):
    x = x@w1.t() + b1
    x = F.relu(x)
    x = x@w2.t() + b2
    x = F.relu(x)
    x = x@w3.t() + b3
    x = F.relu(x)
    return x



optimizer = optim.SGD([w1, b1, w2, b2, w3, b3], 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 = forward(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 = forward(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)))