《PyTorch深度学习实践》11卷积神经网络高级篇

1×1卷积为改变通道数，并且减少计算量，比较省钱

梯度消失的原因：：因为在反向传播过程是每一层的梯度相乘，梯度小于一。当进行一直相乘后导致结果为0，导致梯度消失。

做残差模块有个前提，维度得完全相同，通道、宽度、高度都得一样。

做残差保障输入和输出的通道数是一样的以及大小均得一样，不然无法残差。

如图可知，我们需要保证输入通道和输出通道相同，同时，只有当kernel_size = 3,padding=1, stride=1，才能够保证输入的尺寸和输出的尺寸大小相等。

复现是自己来写代码

扩充视野。

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

##准备数据集

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)

##构建神经网络模型
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 b对应dim=0,w对应宽，h对应高

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 =24*3 + 16
        self.incep1 = InceptionA(in_channels=10)
        self.incep2 = InceptionA(in_channels=20)
        self.mp = nn.MaxPool2d(2)
        self.fc = nn.Linear(1408, 10)
    def forward(self, x):
        in_size = x.size(0)  ##这里的意思获得batchsize
        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)  ##这里的意思是
        x = self.fc(x)
        return x

model = Net()

##搭建损失函数和优化器
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum = 0.5)

##训练模型

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 te():
    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)
        te()