卷积神经网络的原理、实现及变体

发布于:2025-03-26 ⋅ 阅读:(26) ⋅ 点赞:(0)

卷积神经网络convolutional neural network,CNN 是为处理图像数据而生的网络,主要由卷积层(填充和步幅)、池化层(汇聚层)、全连接层组成。

卷积

虽然卷积层得名于卷积(convolution)运算,但我们通常在卷积层中使用更加直观的互相关(cross-correlation)运算。在这里插入图片描述
真实的卷积运算是f(a,b)g(i-a,j-b),其实有一个取反的过程,但是我们实际代码里使用的是互相关运算。
输入的宽度为n,卷积核宽度为k,则输出宽度为n-k+1。
卷积层的参数包括卷积核和偏置,感受野receptive field指的是在前向传播期间影响x计算的所有元素(来自之前所有层)。
一般填充p行在上下,为了上下保持一致,卷积核一般是奇数的长度。输出变为n+p-k+1
滑动步幅为s时,输出变为(n+p-k+s)/s

多输入通道可以:构造相同通道的卷积核,最后对多通道求和输出
多输出通道可以:为每个输出通道o创建一个i*w*h的卷积核,有o个这样的卷积核。
1x1卷积层的作用:看作在每个像素位置应用的全连接层,把i个输入值转换为o个输出层。看这个博主的动图1x1卷积核,没有太明白。文章2 作用:降维/升维,增加非线性,跨通道信息交互。

LeNet

import torch
from torch import nn 
from torchvision import transforms
import torchvision
from torch.utils import data
import matplotlib.pyplot as plt
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=True)
    mnist_test = torchvision.datasets.FashionMNIST(root="../data", train=False, transform=trans, download=True)
    #print(len(mnist_train),len(mnist_test))
    return (data.DataLoader(mnist_train, batch_size, shuffle=True),
        data.DataLoader(mnist_test, batch_size, shuffle=False)) #windows下不能多进程,linux下可以
batch_size=256
train_iter, test_iter = load_data_fashion_mnist(batch_size)

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*5*5,120),
    nn.Sigmoid(),
    nn.Linear(120,84),
    nn.Sigmoid(),
    nn.Linear(84,10)
)

def accuracy(y_hat, y): 
    """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
    return float(cmp.type(y.dtype).sum())
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]
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 = 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):
    """设置matplotlib的轴"""
    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 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 = []
        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):
        # 向图表中添加多个数据点
        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()

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 = Animator(xlabel='epoch', xlim=[1, num_epochs],legend=['train loss', 'train acc', 'test acc'])
    num_batches = 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):
            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])
            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}')

lr, num_epochs = 0.9, 10
def try_gpu(i=0): #@save
    """如果存在,则返回gpu(i),否则返回cpu()"""
    if torch.cuda.device_count() >= i + 1:
        return torch.device(f'cuda:{i}')
    return torch.device('cpu')
train_ch6(net, train_iter, test_iter, num_epochs, lr, try_gpu())

在这里插入图片描述

现代卷积神经网络

AlexNet 第一个击败传统模型的大型神经网络
VGG 使用重复的神经网络块
NiN 重复使用1x1卷积层构造深层网络
GoogLeNet 并行连结的网络
ResNet 残差网络 是计算机视觉最流行的体系架构 特点是跨层数据通路前向传播
DenseNet 是resnet的逻辑扩展(泰勒展开),使用的是cancat而不是相加,主要由稠密层和过渡层(1x1卷积核,降低通道数)构成