Pytorch实战学习(七)：高级CNN

《PyTorch深度学习实践》完结合集_哔哩哔哩_bilibili

Advanced CNN

一、GoogLeNet

Inception Module：而为了减少代码的冗余，将由（卷积（Convolution），池化（Pooling）、全连接（Softmax）以及连接（Other））四个模块所组成的相同的部分，封装成一个类/函数。

1、Inception Module

以卷积核大小(kernel_size)为例，虽然无法具体确定某问题中所应使用的卷积核的大小。但是往往可以有几种备选方案，因此在这个过程中，可以利用这样的网络结构，来将所有的备选方案进行计算，并在后续计算过程中增大最佳方案的权重，以此来达到确定超参数以及训练网络的目的。

最后每个张量沿着通道拼接（Concatenate）在一起时，要保证图像宽度、高度必须相同，通道可以不同

①Average Pooling：均值池化，需要手动设定padding以及stride来保持图像大小（W&H）不变

②1×1 Conv：个数取决于输入张量的通道数，用于改变通道数量

2、1×1 Conv

在1x1卷积中，每个通道的每个像素需要与卷积中的权重进行计算，得到每个通道的对应输出，再进行求和得到一个单通道的总输出，以达到信息融合的目的。即将同一像素位置的多个通道信息整合在同位置的单通道上。

1x1卷积：减少计算量

3、Inception Module代码实现

沿着通道进行拼接，dim设为1（batch-0、channel-1、weight-2、hight-3）

定义一个Inception Module

经过Inception模块输出的通道数：24*3+16=88

4、完整代码

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

# prepare dataset

batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])

train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)

# design model using class

class InceptionA(torch.nn.Module):
    def __init__(self, in_channels):
        super(InceptionA, self).__init__()
        self.branch1x1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)

        self.branch5x5_1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch5x5_2 = torch.nn.Conv2d(16, 24, kernel_size=5, padding=2)

        self.branch3x3_1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)
        self.branch3x3_2 = torch.nn.Conv2d(16, 24, kernel_size=3, padding=1)
        self.branch3x3_3 = torch.nn.Conv2d(24, 24, kernel_size=3, padding=1)

        self.branch_pool = torch.nn.Conv2d(in_channels, 24, kernel_size=1)

    def forward(self, x):
        branch1x1 = self.branch1x1(x)

        branch5x5 = self.branch5x5_1(x)
        branch5x5 = self.branch5x5_2(branch5x5)

        branch3x3 = self.branch3x3_1(x)
        branch3x3 = self.branch3x3_2(branch3x3)
        branch3x3 = self.branch3x3_3(branch3x3)

        branch_pool = F.avg_pool2d(x, kernel_size=3, stride=1, padding=1)
        branch_pool = self.branch_pool(branch_pool)

        outputs = [branch1x1, branch5x5, branch3x3, branch_pool]
        return torch.cat(outputs, dim=1) # b,c,w,h  c对应的是dim=1

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(88, 20, kernel_size=5) # 88 = 24x3 + 16

        self.incep1 = InceptionA(in_channels=10) # 与conv1 中的10对应
        self.incep2 = InceptionA(in_channels=20) # 与conv2 中的20对应

        self.mp = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(1408, 10) 

    def forward(self, x):
        in_size = x.size(0)
        x = F.relu(self.mp(self.conv1(x)))
        x = self.incep1(x)
        x = F.relu(self.mp(self.conv2(x)))
        x = self.incep2(x)
        x = x.view(in_size, -1)
        x = self.fc(x)

        return x

model = Net()
## Device—选择是用GPU还是用CPU训练
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

# training cycle forward, backward, update
def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch+1, batch_idx+1, running_loss/300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('accuracy on test set: %d %% ' % (100*correct/total))

if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()

　

二、ResNet (残差网络)

1、解决梯度消失问题

梯度消失：由于在梯度计算的过程中是用的反向传播，所以需要利用链式法则来进行梯度计算，是一个累乘的过程。若每一个地方梯度都是小于1的，累乘之后的总结果应趋近于0，ω不会再进行进一步的更新

2、跳连接，H(x) = F(x) + x,张量维度必须一样，加完后再激活。不要做pooling，张量的维度会发生变化。

若存在梯度消失现象，即存在某一层网络中的对x求偏导趋近于0

通过加入一个x会使得在方向传播过程中，传播的梯度会保持在1左右，即对x求偏导趋近于1如此，离输入较近的层也可以得到充分的训练。

3、Residual Block

实现 Residual Block，要确保输入和输出维度大小完全一样（等宽等高等通道数）

先是1个卷积层(conv,maxpooling,relu)，然后Residual Block模块，接下来又是一个卷积层(conv,mp,relu),然后Residual Block模块模块，最后一个全连接层(fc)。

4、完整代码

import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
import torch.optim as optim

# prepare dataset

batch_size = 64
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])

train_dataset = datasets.MNIST(root='../dataset/mnist/', train=True, download=True, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='../dataset/mnist/', train=False, download=True, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)

# design model using class

class ResidualBlock(torch.nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        #为了保证 输入和输出 维度相同
        self.channels = channels
        self.conv1 = torch.nn.Conv2d(channels, channels, kernel_size=3, padding=1)
        self.conv2 = torch.nn.Conv2d(channels, channels, kernel_size=3, padding=1)

    def forward(self, x):
        y = F.relu(self.conv1(x))
        y = self.conv2(y)
        # H(x) = F(x) + x，加完以后再Relu
        return F.relu(x + y)

class Net(torch.nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = torch.nn.Conv2d(1, 16, kernel_size=5)
        self.conv2 = torch.nn.Conv2d(16, 32, kernel_size=5) # 88 = 24x3 + 16

        self.rblock1 = ResidualBlock(16)
        self.rblock2 = ResidualBlock(32)

        self.mp = torch.nn.MaxPool2d(2)
        self.fc = torch.nn.Linear(512, 10) # 暂时不知道1408咋能自动出来的

    def forward(self, x):
        in_size = x.size(0)

        x = self.mp(F.relu(self.conv1(x)))
        x = self.rblock1(x)
        x = self.mp(F.relu(self.conv2(x)))
        x = self.rblock2(x)

        x = x.view(in_size, -1)
        x = self.fc(x)
        return x

model = Net()
## Device—选择是用GPU还是用CPU训练
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model.to(device)

# construct loss and optimizer
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)

# training cycle forward, backward, update
def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
        inputs, target = data
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad()

        outputs = model(inputs)
        loss = criterion(outputs, target)
        loss.backward()
        optimizer.step()

        running_loss += loss.item()
        if batch_idx % 300 == 299:
            print('[%d, %5d] loss: %.3f' % (epoch+1, batch_idx+1, running_loss/300))
            running_loss = 0.0

def test():
    correct = 0
    total = 0
    with torch.no_grad():
        for data in test_loader:
            images, labels = data
            images, labels = images.to(device), labels.to(device)
            outputs = model(images)
            _, predicted = torch.max(outputs.data, dim=1)
            total += labels.size(0)
            correct += (predicted == labels).sum().item()
    print('accuracy on test set: %d %% ' % (100*correct/total))

if __name__ == '__main__':
    for epoch in range(10):
        train(epoch)
        test()