CNN——AlexLet

import torch
import torchvision
from torch import nn
from torch.utils.data import Dataset,DataLoader
from torchvision import transforms
from d2l import torch as d2l


def load_data_fashion_mnist(batch_size,resize):
    trans = []
    if resize:
        trans.append(transforms.Resize(size=resize))
    trans.append(transforms.ToTensor())
    transform = transforms.Compose(trans)
    #准备数据集
    train_data = torchvision.datasets.FashionMNIST(root='./data', train=True, transform=transform,
                                                   download=True)
    test_data = torchvision.datasets.FashionMNIST(root='./data', train=False, transform=transform,
                                                  download=True)
    #加载数据集
    train_dataloader = DataLoader(dataset=train_data,batch_size=batch_size,shuffle=True)
    test_dataloader = DataLoader(dataset=test_data,batch_size=batch_size,shuffle=False)

    return train_dataloader,test_dataloader

#搭建网络
class AlexNet(nn.Module):
    def __init__(self):
        super(AlexNet, self).__init__()
        self.model = nn.Sequential(
            nn.Conv2d(1,96,kernel_size=11,stride=4,padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=3,stride=2),
            nn.Conv2d(96,256,kernel_size=5,padding=2),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(256, 384, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.Conv2d(384, 384, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.Conv2d(384, 256, kernel_size=3, padding=1),
            nn.ReLU(),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Flatten(),
            nn.Linear(6400,4096),
            nn.ReLU(),
            nn.Dropout(p=0.5),
            nn.Linear(4096,4096),
            nn.ReLU(),
            nn.Dropout(p=0.5),
            nn.Linear(4096,10)
        )

    def forward(self,x):
        return self.model(x)
    
# Accumulator 实例中创建了 2 个变量，用于分别存储正确预测的数量和预测的总数量
class Accumulator:
    """在`n`个变量上累加。"""
    def __init__(self, n):
        self.data = [0.0] * n

    def add(self, *args):
        self.data = [a + float(b) for a, b in zip(self.data, args)]

    def reset(self):
        self.data = [0.0] * len(self.data)

    def __getitem__(self, idx):
        return self.data[idx]


#GPU训练
def try_gpu(i=0):
    if torch.cuda.device_count() >= 1:
        return torch.device(f'cuda:{i}')
    return torch.device('cpu')


#计算预测正确的数量
def accuracy(y_hat,y):
    if len(y_hat.shape) > 1 and y_hat.shape[1] > 1:
        y_hat = y_hat.argmax(axis=1)
    cmp = y_hat.type(y.dtype) == y
    return float(cmp.type(y.dtype).sum())

#使用GPU计算模型在数据集上的精度
def evaluate_accuracy_gpu(net,data_iter,device=None):
    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 = 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(accuracy(net(X),y),y.numel())
    return metric[0]/metric[1]

def train(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):
        metric = 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], 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)}')


if __name__ == '__main__':
    batch_size = 64
    lr = 0.01
    num_epochs = 10
    net = AlexNet()
    train_iter,test_iter = load_data_fashion_mnist(batch_size=batch_size,resize=224)
    train(net,train_iter=train_iter,test_iter=test_iter,num_epochs=num_epochs,lr=lr,device=try_gpu())
    d2l.plt.show()

loss 0.272, train acc 0.899, test acc 0.893
167.8 examples/sec on cuda:0

总结：

• AlexNet与LeNet架构相似，但是使用了更多的卷积层和更多的参数来拟合大规模的ImageNet数据集