【pytorch李沐动手学深度学习（四、CNN）】

小火龙借个火

已于 2022-04-16 16:00:59 修改

阅读量1.4k

点赞数

文章标签： python pytorch 机器学习人工智能深度学习

于 2022-04-16 15:59:25 首次发布

本文链接：https://blog.csdn.net/weixin_49007132/article/details/124160139

版权

文章目录

卷积神经网络
LeNet
AlexNet
- 网络架构
VGG
NiN
GoogLeNet（并行）
Batch Normalization
ResNet
DenseNet

卷积神经网络

#计算二维互相关运算
def corr2d(X,K):
    h,w=K.shape
    Y=torch.zeros((X.shape[0]-h+1,X.shape[1]-w+1))
    for i in range(Y.shape[0]):
        for j in range(Y.shape[1]):
            Y[i,j]=(X[i:i+h,j:j+w]*K).sum()
        return Y
#conv
class Conv2D(nn.Module):
    def __init__(self,kernal_size):
        super(Conv2D, self).__init__()
        self.weight=nn.Parameter(torch.rand(kernal_size))
        self.bias=nn.Parameter(torch.zeros())#nn.Parameter使其变成可以训练的参数

    def forward(self,X):
        return corr2d(X,self.weight)+self.bias
'''padding and stride'''
def comp_conv2d(conv2d,X):
    X=X.reshape((1,1)+X.shape)#1,1是批度数和通道数
    Y=conv2d(X)
    return Y.reshape(Y.shape[2:])
#设置nn.Conv2d参数，前两个参数是输入输出通道
conv2d=nn.Conv2d(1,1,kernel_size=3,padding=1)#p=k-1
conv2d=nn.Conv2d(1,1,kernel_size=(5,3),padding=(2,1))
conv2d = nn.Conv2d(1, 1, kernel_size=3, padding=1, stride=2)
conv2d = nn.Conv2d(1, 1, kernel_size=(3, 5), padding=(0, 1), stride=(3, 4))
#多输入通道
def corr2d_multi_in(X,K):
    return sum(d2l.corr2d(x,k) for x,k in zip(X,K))
#多输出
def corr2d_multi_in_out(X, K):
    # 迭代“K”的第0个维度，每次都对输入“X”执行互相关运算。
    # 最后将所有结果都叠加在一起
    return torch.stack([corr2d_multi_in(X, k) for k in K], 0)
#1*1conv
def corr2d_multi_in_out_1x1(X, K):
    c_i, h, w = X.shape
    c_o = K.shape[0]
    X = X.reshape((c_i, h * w))
    K = K.reshape((c_o, c_i))
    # 全连接层中的矩阵乘法
    Y = torch.matmul(K, X)
    return Y.reshape((c_o, h, w))

#pooling
pool2d=nn.MaxPool2d(3,padding=1,stride=2)

LeNet

在这里插入图片描述

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))

在这里插入图片描述

AlexNet

在这里插入图片描述

d2l.evaluate_accuracy_gpu(net, data_iter, device=None)#评估精度gpu

网络架构

net = nn.Sequential(
    # 这里，我们使用一个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，而非论文中的1000
    nn.Linear(4096, 10))

因为pytorch不可以自动计算输出通道数，可以使用下面代码得到输出通道数，nn.Flatten()之后为6400

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

VGG

在这里插入图片描述
vgg相当于把大卷积核做小，例如把1个55卷积核换成两个33卷积核，这样输出大小依然不变。原始VGG网络有5个卷积块，其中前两个块各有一个卷积层，后三个块各包含两个卷积层。第一个模块有64个输出通道，每个后续模块将输出通道数量翻倍，直到该数字达到512。由于该网络使用8个卷积层和3个全连接层，因此它通常被称为VGG-11。

def vgg_block(num_convs, in_channels, out_channels):
    layers = []
    for _ in range(num_convs):
        layers.append(nn.Conv2d(in_channels, out_channels,
                                kernel_size=3, padding=1))
        layers.append(nn.ReLU())
        in_channels = out_channels
    layers.append(nn.MaxPool2d(kernel_size=2,stride=2))
    return nn.Sequential(*layers)
conv_arch = ((1, 64), (1, 128), (2, 256), (2, 512), (2, 512))
def vgg(conv_arch):
    conv_blks = []
    in_channels = 1
    # 卷积层部分
    for (num_convs, out_channels) in conv_arch:
        conv_blks.append(vgg_block(num_convs, in_channels, out_channels))
        in_channels = out_channels

    return nn.Sequential(
        *conv_blks, nn.Flatten(),
        # 全连接层部分
        nn.Linear(out_channels * 7 * 7, 4096), nn.ReLU(), nn.Dropout(0.5),
        nn.Linear(4096, 4096), nn.ReLU(), nn.Dropout(0.5),
        nn.Linear(4096, 10))

net = vgg(conv_arch)

NiN

在这里插入图片描述
NiN块以一个普通卷积层开始，后面是两个11的卷积层。这两个11卷积层充当带有ReLU激活函数的逐像素全连接层。第一层的卷积窗口形状通常由用户设置。随后的卷积窗口形状固定为1*1。

#nin块
def nin_block(in_channels, out_channels, kernel_size, strides, padding):
    return nn.Sequential(
        nn.Conv2d(in_channels, out_channels, kernel_size, strides, padding),
        nn.ReLU(),
        nn.Conv2d(out_channels, out_channels, kernel_size=1), nn.ReLU(),
        nn.Conv2d(out_channels, out_channels, kernel_size=1), nn.ReLU())
#网络
net = nn.Sequential(
    nin_block(1, 96, kernel_size=11, strides=4, padding=0),
    nn.MaxPool2d(3, stride=2),
    nin_block(96, 256, kernel_size=5, strides=1, padding=2),
    nn.MaxPool2d(3, stride=2),
    nin_block(256, 384, kernel_size=3, strides=1, padding=1),
    nn.MaxPool2d(3, stride=2),
    nn.Dropout(0.5),
    # 标签类别数是10
    nin_block(384, 10, kernel_size=3, strides=1, padding=1),
    nn.AdaptiveAvgPool2d((1, 1)),
    # 将四维的输出转成二维的输出，其形状为(批量大小,10)
    nn.Flatten())

GoogLeNet（并行）

在这里插入图片描述

class Inception(nn.Module):
    # c1--c4是每条路径的输出通道数
    def __init__(self, in_channels, c1, c2, c3, c4, **kwargs):
        super(Inception, self).__init__(**kwargs)
        # 线路1，单1x1卷积层
        self.p1_1 = nn.Conv2d(in_channels, c1, kernel_size=1)
        # 线路2，1x1卷积层后接3x3卷积层
        self.p2_1 = nn.Conv2d(in_channels, c2[0], kernel_size=1)
        self.p2_2 = nn.Conv2d(c2[0], c2[1], kernel_size=3, padding=1)
        # 线路3，1x1卷积层后接5x5卷积层
        self.p3_1 = nn.Conv2d(in_channels, c3[0], kernel_size=1)
        self.p3_2 = nn.Conv2d(c3[0], c3[1], kernel_size=5, padding=2)
        # 线路4，3x3最大汇聚层后接1x1卷积层
        self.p4_1 = nn.MaxPool2d(kernel_size=3, stride=1, padding=1)
        self.p4_2 = nn.Conv2d(in_channels, c4, kernel_size=1)

    def forward(self, x):
        p1 = F.relu(self.p1_1(x))
        p2 = F.relu(self.p2_2(F.relu(self.p2_1(x))))
        p3 = F.relu(self.p3_2(F.relu(self.p3_1(x))))
        p4 = F.relu(self.p4_2(self.p4_1(x)))
        # 在通道维度上连结输出
        return torch.cat((p1, p2, p3, p4), dim=1)

# 连接通道维度上每个块的输入和输出
            X = torch.cat((X, Y), dim=1)

在这里插入图片描述

b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b2 = nn.Sequential(nn.Conv2d(64, 64, kernel_size=1),
                   nn.ReLU(),
                   nn.Conv2d(64, 192, kernel_size=3, padding=1),
                   nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
b3 = nn.Sequential(Inception(192, 64, (96, 128), (16, 32), 32),
                   Inception(256, 128, (128, 192), (32, 96), 64),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))  
b4 = nn.Sequential(Inception(480, 192, (96, 208), (16, 48), 64),
                   Inception(512, 160, (112, 224), (24, 64), 64),
                   Inception(512, 128, (128, 256), (24, 64), 64),
                   Inception(512, 112, (144, 288), (32, 64), 64),
                   Inception(528, 256, (160, 320), (32, 128), 128),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))                                    
b5 = nn.Sequential(Inception(832, 256, (160, 320), (32, 128), 128),
                   Inception(832, 384, (192, 384), (48, 128), 128),
                   nn.AdaptiveAvgPool2d((1,1)),
                   nn.Flatten())

net = nn.Sequential(b1, b2, b3, b4, b5, nn.Linear(1024, 10))

Batch Normalization

Batch Normalization层

nn.BatchNorm2d(6)#6为输入通道数

ResNet

在这里插入图片描述
残差块

class Residual(nn.Module):  #@save
    def __init__(self, input_channels, num_channels,
                 use_1x1conv=False, strides=1):
        super().__init__()
        self.conv1 = nn.Conv2d(input_channels, num_channels,
                               kernel_size=3, padding=1, stride=strides)
        self.conv2 = nn.Conv2d(num_channels, num_channels,
                               kernel_size=3, padding=1)
        if use_1x1conv:
            self.conv3 = nn.Conv2d(input_channels, num_channels,
                                   kernel_size=1, stride=strides)
        else:
            self.conv3 = None
        self.bn1 = nn.BatchNorm2d(num_channels)
        self.bn2 = nn.BatchNorm2d(num_channels)

    def forward(self, X):
        Y = F.relu(self.bn1(self.conv1(X)))
        Y = self.bn2(self.conv2(Y))
        if self.conv3:
            X = self.conv3(X)
        Y += X
        return F.relu(Y)

ResNet模型

b1 = nn.Sequential(nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
                   nn.BatchNorm2d(64), nn.ReLU(),
                   nn.MaxPool2d(kernel_size=3, stride=2, padding=1))
def resnet_block(input_channels, num_channels, num_residuals,
                 first_block=False):
    blk = []
    for i in range(num_residuals):
        if i == 0 and not first_block:
            blk.append(Residual(input_channels, num_channels,
                                use_1x1conv=True, strides=2))
        else:
            blk.append(Residual(num_channels, num_channels))
    return blk
b2 = nn.Sequential(*resnet_block(64, 64, 2, first_block=True))
b3 = nn.Sequential(*resnet_block(64, 128, 2))
b4 = nn.Sequential(*resnet_block(128, 256, 2))
b5 = nn.Sequential(*resnet_block(256, 512, 2))
net = nn.Sequential(b1, b2, b3, b4, b5,
                    nn.AdaptiveAvgPool2d((1,1)),
                    nn.Flatten(), nn.Linear(512, 10))

DenseNet

在这里插入图片描述

#稠密块
def conv_block(input_channels, num_channels):
    return nn.Sequential(
        nn.BatchNorm2d(input_channels), nn.ReLU(),
        nn.Conv2d(input_channels, num_channels, kernel_size=3, padding=1))
class DenseBlock(nn.Module):
    def __init__(self, num_convs, input_channels, num_channels):
        super(DenseBlock, self).__init__()
        layer = []
        for i in range(num_convs):
            layer.append(conv_block(
                num_channels * i + input_channels, num_channels))
        self.net = nn.Sequential(*layer)

    def forward(self, X):
        for blk in self.net:
            Y = blk(X)
            # 连接通道维度上每个块的输入和输出
            X = torch.cat((X, Y), dim=1)
        return X

过渡层：由于每个稠密块都会带来通道数的增加，使用过多则会过于复杂化模型。而过渡层可以用来控制模型复杂度。它通过1*1卷积层来减小通道数，并使用步幅为2的平均汇聚层减半高和宽，从而进一步降低模型复杂度

def transition_block(input_channels, num_channels):
    return nn.Sequential(
        nn.BatchNorm2d(input_channels), nn.ReLU(),
        nn.Conv2d(input_channels, num_channels, kernel_size=1),
        nn.AvgPool2d(kernel_size=2, stride=2))

DenseNet首先使用同ResNet一样的单卷积层和最大汇聚层

b1 = nn.Sequential(
    nn.Conv2d(1, 64, kernel_size=7, stride=2, padding=3),
    nn.BatchNorm2d(64), nn.ReLU(),
    nn.MaxPool2d(kernel_size=3, stride=2, padding=1))

DenseNet使用过渡层来减半高和宽，并减半通道数

# num_channels为当前的通道数
num_channels, growth_rate = 64, 32
num_convs_in_dense_blocks = [4, 4, 4, 4]
blks = []
for i, num_convs in enumerate(num_convs_in_dense_blocks):
    blks.append(DenseBlock(num_convs, num_channels, growth_rate))
    # 上一个稠密块的输出通道数
    num_channels += num_convs * growth_rate
    # 在稠密块之间添加一个转换层，使通道数量减半
    if i != len(num_convs_in_dense_blocks) - 1:
        blks.append(transition_block(num_channels, num_channels // 2))
        num_channels = num_channels // 2

接上全局汇聚层和全连接层来输出结果

net = nn.Sequential(
    b1, *blks,
    nn.BatchNorm2d(num_channels), nn.ReLU(),
    nn.AdaptiveAvgPool2d((1, 1)),
    nn.Flatten(),
    nn.Linear(num_channels, 10))

小火龙借个火

关注

0
点赞
踩
2

收藏

觉得还不错? 一键收藏
0
评论
【pytorch李沐动手学深度学习（四、CNN）】

文章目录一、卷积神经网络二、LeNet三、AlexNet网络架构VGGNiNGoogLeNet（并行）Batch NormalizationResNetDenseNet总结一、卷积神经网络#计算二维互相关运算def corr2d(X,K): h,w=K.shape Y=torch.zeros((X.shape[0]-h+1,X.shape[1]-w+1)) for i in range(Y.shape[0]): for j in range(Y.shape[1
复制链接

扫一扫