深度学习 —— 个人学习笔记11（AlexNet）

声明

  本文章为个人学习使用，版面观感若有不适请谅解，文中知识仅代表个人观点，若出现错误，欢迎各位批评指正。

二十三、深度卷积神经网络（AlexNet）

import torch
import torchvision
from torch import nn
from IPython import display
from torch.utils import data
import time
from torchvision import transforms
import matplotlib.pyplot as plt
from matplotlib_inline import backend_inline

mydevice = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")

def accuracy(y_hat, y):                                                           # 定义一个函数来为预测正确的数量计数
    """计算预测正确的数量"""
    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                                                # bool 类型，若预测结果与实际结果一致，则为 True
    return float(cmp.type(y.dtype).sum())

def evaluate_accuracy_gpu(net, data_iter, device=None):
    """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 = 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(accuracy(net(X), y), y.numel())
    return metric[0] / metric[1]

def set_axes(axes, xlabel, ylabel, xlim, ylim, xscale, yscale, legend):
    axes.set_xlabel(xlabel), axes.set_ylabel(ylabel)
    axes.set_xscale(xscale), axes.set_yscale(yscale)
    axes.set_xlim(xlim),     axes.set_ylim(ylim)
    if legend:
        axes.legend(legend)
    axes.grid()

class Accumulator:                                                                # 定义一个实用程序类 Accumulator，用于对多个变量进行累加
    """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]

class Animator:                                                                   # 定义一个在动画中绘制数据的实用程序类 Animator
    """在动画中绘制数据"""
    def __init__(self, xlabel=None, ylabel=None, legend=None, xlim=None,
                 ylim=None, xscale='linear', yscale='linear',
                 fmts=('-', 'm--', 'g-.', 'r:'), nrows=1, ncols=1,
                 figsize=(3.5, 2.5)):
        # 增量地绘制多条线
        if legend is None:
            legend = []
        backend_inline.set_matplotlib_formats('svg')
        self.fig, self.axes = plt.subplots(nrows, ncols, figsize=figsize)
        if nrows * ncols == 1:
            self.axes = [self.axes, ]
        # 使用lambda函数捕获参数
        self.config_axes = lambda: set_axes(
            self.axes[0], xlabel, ylabel, xlim, ylim, xscale, yscale, legend)
        self.X, self.Y, self.fmts = None, None, fmts

    def add(self, x, y):
        # Add multiple data points into the figure
        if not hasattr(y, "__len__"):
            y = [y]
        n = len(y)
        if not hasattr(x, "__len__"):
            x = [x] * n
        if not self.X:
            self.X = [[] for _ in range(n)]
        if not self.Y:
            self.Y = [[] for _ in range(n)]
        for i, (a, b) in enumerate(zip(x, y)):
            if a is not None and b is not None:
                self.X[i].append(a)
                self.Y[i].append(b)
        self.axes[0].cla()
        for x, y, fmt in zip(self.X, self.Y, self.fmts):
            self.axes[0].plot(x, y, fmt)
        self.config_axes()
        display.display(self.fig)
        # 通过以下两行代码实现了在PyCharm中显示动图
        plt.draw()
        plt.pause(interval=0.001)
        display.clear_output(wait=True)
        plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']

class Timer:
    def __init__(self):
        self.times = []
        self.start()

    def start(self):
        self.tik = time.time()

    def stop(self):
        self.times.append(time.time() - self.tik)
        return self.times[-1]

    def sum(self):
        """Return the sum of time."""
        return sum(self.times)

def load_data_fashion_mnist(batch_size, resize=None):
    """下载 Fashion-MNIST 数据集，然后将其加载到内存中"""
    trans = [transforms.ToTensor()]
    if resize:
        trans.insert(0, transforms.Resize(resize))
    trans = transforms.Compose(trans)
    mnist_train = torchvision.datasets.FashionMNIST(
        root="../data", train=True, transform=trans, download=False)
    mnist_test = torchvision.datasets.FashionMNIST(
        root="../data", train=False, transform=trans, download=False)
    return (data.DataLoader(mnist_train, batch_size, shuffle=True,
                            num_workers=4),
            data.DataLoader(mnist_test, batch_size, shuffle=False,
                            num_workers=4))

def train(net, train_iter, test_iter, num_epochs, lr, device):
    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', torch.cuda.get_device_name(device))
    net.to(device)
    optimizer = torch.optim.SGD(net.parameters(), lr=lr)
    loss = nn.CrossEntropyLoss()
    animator = Animator(xlabel='epoch', xlim=[1, num_epochs],
                            legend=['train loss', 'train acc', 'test acc'])
    timer, num_batches = 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 = 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))
    plt.title(f'loss {train_l:.3f}, train acc {train_acc:.3f}, test acc {test_acc:.3f}\n'
              f'{metric[2] * num_epochs / timer.sum():.1f} examples/sec on {str(device)}')
    plt.show()

net = nn.Sequential(
    # 这里使用一个 11*11 的更大窗口来捕捉对象。
    # 同时，步幅为 4，以减少输出的高度和宽度。
    # 另外，输出通道的数目远大于 LeNet
    nn.Conv2d(1, 96, kernel_size=11, stride=4, padding=1), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    # 减小卷积窗口，使用填充为2来使得输入与输出的高和宽一致，且增大输出通道数
    nn.Conv2d(96, 256, kernel_size=5, padding=2), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2),
    # 使用三个连续的卷积层和较小的卷积窗口。
    # 除了最后的卷积层，输出通道的数量进一步增加。
    # 在前两个卷积层之后，汇聚层不用于减少输入的高度和宽度
    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(),
    # 这里，全连接层的输出数量是 LeNet 中的好几倍。使用 dropout 层来减轻过拟合
    nn.Linear(6400, 4096), nn.ReLU(),
    nn.Dropout(p=0.5),
    nn.Linear(4096, 4096), nn.ReLU(),
    nn.Dropout(p=0.5),
    # 最后是输出层。由于这里使用Fashion-MNIST，所以用类别数为10
    nn.Linear(4096, 10))

X = torch.randn(1, 1, 224, 224)
for layer in net:
    X=layer(X)
    print(layer.__class__.__name__,'output shape:\t\t', X.shape)

batch_size = 128
train_iter, test_iter = load_data_fashion_mnist(batch_size, resize=224)

lr, num_epochs = 0.01, 5
train(net, train_iter, test_iter, num_epochs, lr, mydevice)

---

  文中部分知识参考：B 站 —— 跟李沐学AI；百度百科