P23 LeNet经典神经网络模型

LeNet(LeNet-5) 由两个部分组成：卷积编码器和全连接层密集块

import torch
from matplotlib import pyplot as plt
from torch import nn
from d2l import torch as d2l

class Reshape(torch.nn.Module): #原始输入是32*32
    def forward(self,x):
        return x.view(-1,1,28,28)
    #28*28的图片

net = torch.nn.Sequential(
    Reshape(),nn.Conv2d(1, 6, kernel_size = 5, padding=2 ),nn.Sigmoid(),
    #kernel的窗口是5*5，因为原始数据是32*32，当它变成28*28的时候，等于少了边缘，这里补上，padding=2
    #在卷积后加入sigmoid函数
    nn.AvgPool2d(kernel_size=2, stride=2), #用平均池化
    nn.Conv2d(6, 16, kernel_size=5), nn.Sigmoid(),
    #卷积层输入是6，kernel还是5，这里不作padding，结束后继续做sigmoid
    nn.AvgPool2d(kernel_size=2, stride=2), nn.Flatten(),
    #接上平均池化，和上一层一样，但是最后要把输出变成1维的向量，所以用flatten
    nn.Linear(16*5*5,120),nn.Sigmoid(),
    #高和宽在池化后，输出是120,16*5*5是最后一层的输出
    nn.Linear(120,84),nn.Sigmoid(),
    #把120降到84
    nn.Linear (84,10))
    #最后降到10，因为他有10个类别
    #2个卷积层+1个激活层+池化层

验证函数

X = torch.rand(size=(1,1,28,28),dtype=torch.float32)
for layer in net:
    X = layer(X)
    print(layer.__class__.__name__,'output shape:\t',X.shape)

打印结果：和书上的图例一样，代码显示的是书上的图例

Reshape output shape:    torch.Size([1, 1, 28, 28])
第一个是batch size=1， 通道=1，输入大小28*28
Conv2d output shape:    torch.Size([1, 6, 28, 28])
到了这里，通道变成了6
Sigmoid output shape:   torch.Size([1, 6, 28, 28])
AvgPool2d output shape:     torch.Size([1, 6, 14, 14])
第一个模块结束，输出是14*14，但是通道变成了6

Conv2d output shape:    torch.Size([1, 16, 10, 10])
Sigmoid output shape:   torch.Size([1, 16, 10, 10])
AvgPool2d output shape:     torch.Size([1, 16, 5, 5])
第二个模块结束，高和宽被减了3倍，通道数从6变成16，是MLP的思想，慢慢把一个很长的向量往下压，最后输出是5*5
卷积把图片大小渐渐变小，但是通道慢慢变多，把空间信息压缩，把抽出来压缩的信息放在不同通道里
最后通过一个多层感知机模型，能训练到最后的输出，极端一点图片大小会变成1，通道会有几千，最后做全连接输出

Flatten output shape:   torch.Size([1, 400])
Linear output shape:    torch.Size([1, 120])
Sigmoid output shape:   torch.Size([1, 120])
Linear output shape:    torch.Size([1, 84])
Sigmoid output shape:   torch.Size([1, 84])
Linear output shape:    torch.Size([1, 10])

LeNet在Fashion-MNIST上实现

batch_size = 256
train_iter, test_iter =d2l.load_data_fashion_mnist(batch_size=batch_size)

def evaluate_accuracy_gpu(net, data_iter, device=None): #@save
    """使用GPU计算模型在数据集上的精度"""
    if isinstance(net, nn.Module):
        net.eval()  # 设置为评估模式
        if not device:
            device = next(iter(net.parameters())).device
    # 正确预测的数量，总预测的数量
    metric = d2l.Accumulator(2)
    with torch.no_grad():
        for X, y in data_iter:
            if isinstance(X, list):
                # BERT微调所需的（之后将介绍）
                X = [x.to(device) for x in X]
            else:
                X = X.to(device)
            y = y.to(device)
            metric.add(d2l.accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]

def train_ch6(net, train_iter, test_iter, num_epochs, lr, device):
    """用GPU训练模型(在第六章定义)"""
    def init_weights(m):
        if type(m) == nn.Linear or type(m) == nn.Conv2d:
            nn.init.xavier_uniform_(m.weight)
    net.apply(init_weights)
    print('training on', device)
    net.to(device)
    optimizer = torch.optim.SGD(net.parameters(), lr=lr)
    loss = nn.CrossEntropyLoss()
    animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],
                            legend=['train loss', 'train acc', 'test acc'])
    timer, num_batches = d2l.Timer(), len(train_iter)
    for epoch in range(num_epochs):
        # 训练损失之和，训练准确率之和，样本数
        metric = d2l.Accumulator(3)
        net.train()
        for i, (X, y) in enumerate(train_iter):
            timer.start()
            optimizer.zero_grad()
            X, y = X.to(device), y.to(device)
            y_hat = net(X)
            l = loss(y_hat, y)
            l.backward()
            optimizer.step()
            with torch.no_grad():
                metric.add(l * X.shape[0], d2l.accuracy(y_hat, y), X.shape[0])
            timer.stop()
            train_l = metric[0] / metric[2]
            train_acc = metric[1] / metric[2]
            if (i + 1) % (num_batches // 5) == 0 or i == num_batches - 1:
                animator.add(epoch + (i + 1) / num_batches,(train_l, train_acc, None))
                plt.show()
        test_acc = evaluate_accuracy_gpu(net, test_iter)
        animator.add(epoch + 1, (None, None, test_acc))
        plt.show()

    print(f'loss {train_l:.3f}, train acc {train_acc:.3f}, '
          f'test acc {test_acc:.3f}')
    print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec '
          f'on {str(device)}')
    plt.show()

训练和评估LeNet-5模型

lr, num_epochs = 0.9,10
train_ch6(net,train_iter,test_iter,num_epochs,lr,d2l.try_gpu())
plt.show()

打印结果：

loss 0.467, train acc 0.825, test acc 0.767
10168.4 examples/sec on cpu

动画不能像视频里那样动态显示