LeNet网络的实现

python 复制代码

import torch
from torch import nn
from d2l import torch as d2l

x = 28
net = nn.Sequential(
    nn.Conv2d(1, 6, kernel_size=5, padding=2), nn.Sigmoid(),
    nn.AvgPool2d(kernel_size=2, stride=2),
    nn.Conv2d(6, 16, kernel_size=5), nn.Sigmoid(),
    nn.AvgPool2d(kernel_size=2, stride=2),
    nn.Flatten(),
    nn.Linear(16 * (x/4 - 2) * (x/4 - 2), 120), nn.Sigmoid(),
    nn.Linear(120, 84), nn.Sigmoid(),
    nn.Linear(84, 10))

输入图像是单通道 x*x大小

卷积层。
输入一个通道，输出六个通道，卷积核大小5*5，填充2，步幅1,因此输出图像大小不变。
平均汇聚层。
核大小2*2，步幅2，因此输出图像大小减半。（x/2)(x/2）
卷积层。
输入6通道，输出16通道，核大小5，输出图像大小减4.(x/2-4) (x/2 - 4)
平均汇聚层。
核大小2*2，步幅2，输出大小减半。(x/4-2)(x/4-2)
全连接层。
输入大小： 16 * (x/4 - 2) * (x/4 - 2)
输出大小： 10

测试函数

python 复制代码

def evaluate_accuracy_gpu(net , data_iter,device=None):
    if isinstance(net , nn.Module):
        net.eval()
        if not device:
            # 获取第一个参数所在的设备，把以后的数据放在同一个设备上
            device = next(iter(net.parameters())).device
        metric = d2l.Accumulator(2)
        with torch.no_grad():
            for X , y in data_iter:
                if isinstance(X , list):
                    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]

训练和测试

python 复制代码

def train_ch6(net , train_iter , test_iter, num_epochs , lr ,device):
    # 初始化权重
    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)
    # 优化器  
    optimizer = torch.optim.SGD(net.parameters(), lr)
    # 损失函数
    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):
        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))
        test_acc = evaluate_accuracy_gpu(net , test_iter)
        animator.add(epoch+1 ,(None , None , test_acc))
    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)}')