LeNet网络

一、定义模型

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

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()    # 第一维的batch保持住，后面的维度拉成一个向量
    ,nn.Linear(16*5*5,120)
    ,nn.Sigmoid()
    ,nn.Linear(120,84)
    ,nn.Sigmoid()
    ,nn.Linear(84,10)
)

二、查看每一步操作后的维度信息

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)

三、模型训练

加载数据包

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

将数据放入GPU(无GPU不影响)，返回的是准确率

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  不更新参数
        if not device:
            device = next(iter(net.parameters())).device   # 第一个参数拿出来看在哪
    # 正确预测的数量，总预测的数量
    metric = d2l.Accumulator(2)    # 累加器
    with torch.no_grad():
        for X, y in data_iter:
            if isinstance(X, list):    # 判断X是否为一个列表
                # BERT微调所需的（之后将介绍）
                X = [x.to(device) for x in X]   # 是列表一个一个加入device
            else:
                X = X.to(device)   # 是tensor 一次性加入
            y = y.to(device)
            metric.add(d2l.accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]     # 返回的是准确率

训练函数

#@save
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)     # 查看在哪训练程序
    
    net.to(device)
    optimizer = torch.optim.SGD(net.parameters(), lr=lr)
    loss = nn.CrossEntropyLoss()
    
    # 动画效果
    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)    # 每个epoch会重新记0
        net.train()    # train模式 参数更新
        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}')
    
                     # 打印每秒计算多少个样本
    print(f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec '
          f'on {str(device)}')

训练和评估模型

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