CNN进阶 | 关于Inception Module与 Residual network | MNIST数据集

1. 关于GoogleNet：

2. Inception Module

3. 1*1 Convolution：

为什么使用1*1的卷积：

节省训练时间

4. Inception Module 的实现

代码：

import torch
import torch.nn as nn
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,))])  # 归一化,均值和方差

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


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

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

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

        self.branch_pool = 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(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = 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 = nn.MaxPool2d(2)
        self.fc = 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()

# 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
        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
            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()

[1,   300] loss: 0.931
[1,   600] loss: 0.190
[1,   900] loss: 0.129
accuracy on test set: 97 % 
[2,   300] loss: 0.105
[2,   600] loss: 0.088
[2,   900] loss: 0.083
accuracy on test set: 97 % 
[3,   300] loss: 0.074
[3,   600] loss: 0.074
[3,   900] loss: 0.066
accuracy on test set: 98 % 
[4,   300] loss: 0.063
[4,   600] loss: 0.062
[4,   900] loss: 0.055
accuracy on test set: 98 % 
[5,   300] loss: 0.058
[5,   600] loss: 0.052
[5,   900] loss: 0.052
accuracy on test set: 98 % 
[6,   300] loss: 0.047
[6,   600] loss: 0.051
[6,   900] loss: 0.047
accuracy on test set: 98 % 
[7,   300] loss: 0.044
[7,   600] loss: 0.043
[7,   900] loss: 0.043
accuracy on test set: 98 % 
[8,   300] loss: 0.041
[8,   600] loss: 0.041
[8,   900] loss: 0.039
accuracy on test set: 98 % 
[9,   300] loss: 0.033
[9,   600] loss: 0.039
[9,   900] loss: 0.038
accuracy on test set: 98 % 
[10,   300] loss: 0.033
[10,   600] loss: 0.039
[10,   900] loss: 0.031
accuracy on test set: 98 % 

5. 运行结果：

6. 关于梯度消失：

7. 关于Residual network

8. Residual network的实现

代码：

import torch
import torch.nn as nn
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,))]) # 归一化,均值和方差
 
train_dataset = datasets.MNIST(root='./dataset/mnist/', train=True, download=False, transform=transform)
train_loader = DataLoader(train_dataset, shuffle=True, batch_size=batch_size)
test_dataset = datasets.MNIST(root='./dataset/mnist/', train=False, download=False, transform=transform)
test_loader = DataLoader(test_dataset, shuffle=False, batch_size=batch_size)
 
# design model using class
class ResidualBlock(nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        self.channels = channels
        self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
        self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
 
    def forward(self, x):
        y = F.relu(self.conv1(x))
        y = self.conv2(y)
        return F.relu(x + y)
 
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(1, 16, kernel_size=5)
        self.conv2 = nn.Conv2d(16, 32, kernel_size=5) # 88 = 24x3 + 16
 
        self.rblock1 = ResidualBlock(16)
        self.rblock2 = ResidualBlock(32)
 
        self.mp = nn.MaxPool2d(2)
        self.fc = 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()
 
# 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
        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
            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()

[1,   300] loss: 0.543
[1,   600] loss: 0.145
[1,   900] loss: 0.123
accuracy on test set: 97 % 
[2,   300] loss: 0.089
[2,   600] loss: 0.080
[2,   900] loss: 0.067
accuracy on test set: 97 % 
[3,   300] loss: 0.058
[3,   600] loss: 0.057
[3,   900] loss: 0.054
accuracy on test set: 98 % 
[4,   300] loss: 0.045
[4,   600] loss: 0.047
[4,   900] loss: 0.047
accuracy on test set: 98 % 
[5,   300] loss: 0.038
[5,   600] loss: 0.040
[5,   900] loss: 0.038
accuracy on test set: 98 % 
[6,   300] loss: 0.033
[6,   600] loss: 0.036
[6,   900] loss: 0.031
accuracy on test set: 98 % 
[7,   300] loss: 0.027
[7,   600] loss: 0.032
[7,   900] loss: 0.028
accuracy on test set: 98 % 
[8,   300] loss: 0.028
[8,   600] loss: 0.025
[8,   900] loss: 0.027
accuracy on test set: 98 % 
[9,   300] loss: 0.020
[9,   600] loss: 0.025
[9,   900] loss: 0.024
accuracy on test set: 98 % 
[10,   300] loss: 0.021
[10,   600] loss: 0.024
[10,   900] loss: 0.020
accuracy on test set: 99 % 

9. 使用Residual network的效果