Pytorch-多分类问题神经层和训练部分代码的构建

import torch
import torch.nn.functional as F


# 先建立三个线性层结构
# 建立 784=>200=>200=>10的结构

w1, b1 = torch.randn(200, 784, requires_grad=True),\
         torch.randn(200, requires_grad=True)
# 之前讲过，括号内分别为（ch_out, ch_in），784是28*28乘积得来，对于常用的mnist数据集，多采用这种像素
w2, b2 = torch.randn(200, 200, requires_grad=True),\
         torch.randn(200, requires_grad=True)
# 每个层均具有w、b参数
w3, b3 = torch.randn(10, 200, requires_grad=True),\
         torch.randn(10, requires_grad=True)

# 中间层虽然前后输出维度相同，均是200，但并不是没有作用，而是经历了特征变换的过程
# 进行了[784, 200]=>[200, 200]=>[200, 10]的降维变换

# 将forward过程写进一个函数里面
def forward(x):
    x = x@w1.t() + b1
    # 进行矩阵相乘
    x = F.relu(x)
    # 使用relu激活函数
    x = x@w2.t() + b2
    x = F.relu(x)
    x = x@w3.t() + b3
    x = F.relu(x)
    return x
# 注意 这里返回的x是logits，没有经过sigmoid和softmax

# 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
learning_rate = 1e-3
optimizer = optim.SGD([w1, b1, w2, b2, w3, b3], lr=learning_rate)
# 这里优化器优化的目标是三种全连接层的变量
criteon = nn.CrossEntropyLoss()
# 这里使用的是crossentropyloss

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)))