卷积神经网络(高级篇)《PyTorch深度学习实践》

构造神经网络时一些超参数比较难选,比如 kernal卷积核 大小
串型
GoogleNet:把集中卷积核都作为候选
1.Inception Module

1*1卷积核:输入不同通道相同位置的信息的融合
作用:改变通道数量以减低运算量
实现Inception Module(如下图)
卷积神经网络(高级篇)《PyTorch深度学习实践》_第1张图片
构建网络:先是1个卷积层(conv,maxpooling,relu),然后inceptionA模块(输出的channels是24+16+24+24=88),接下来又是一个卷积层(conv,mp,relu),然后inceptionA模块,最后一个全连接层(fc)。

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=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(nn.Module):
    def __init__(self, in_channels):
        super(InceptionA, self).__init__()
        self.branch1x1 = nn.Conv2d(in_channels, 16, kernel_size=1) #1*1卷积
 
        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)#宽高不变
 
        self.branch_pool = nn.Conv2d(in_channels, 24, kernel_size=1) #实例的卷积
 
    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) #均值池化,形状不变的池化
        branch_pool = self.branch_pool(branch_pool) #可调用callable 先池化再卷积
 
        outputs = [branch1x1, branch5x5, branch3x3, branch_pool]
        return torch.cat(outputs, dim=1) # [b,c,w,h]沿着c拼起来即 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()

2.可能会产生梯度消失的问题
Residual net(ResNet)残差网络
解决方法:采用跳连接(如下图)
F(x)+x 要求 输出和x张量维度必须相同
ResidualNet内部结构(如下图)
卷积神经网络(高级篇)《PyTorch深度学习实践》_第2张图片
构建网络:先是1个卷积层(conv,maxpooling,relu),然后ResidualBlock模块,接下来又是一个卷积层(conv,mp,relu),然后esidualBlock模块模块,最后一个全连接层(fc)
卷积神经网络(高级篇)《PyTorch深度学习实践》_第3张图片

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=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(nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        self.channels = channels
        self.conv1 = nn.Conv2d(channels, channels, kernel_size=3, padding=1) #输入输出通道同
        self.conv2 = nn.Conv2d(channels, channels, kernel_size=3, padding=1)
 
    def forward(self, x):
        y = F.relu(self.conv1(x))#卷积后激活
        y = self.conv2(y)#卷积
        return F.relu(x + y)#加一起 再激活
 
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)
 
        self.rblock1 = ResidualBlock(16)
        self.rblock2 = ResidualBlock(32)
 
        self.mp = nn.MaxPool2d(2)
        self.fc = nn.Linear(512, 10) 
 
 
    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.理论《深度学习》
2.阅读pytorch文档(通读一遍)了解其中的一些公式
3.复现经典工作(读代码,写代码)
4.扩充视野

你可能感兴趣的