《PyTorch深度学习实践》P11卷积神经网络高级篇

全部代码在最后面。
GoogLeNet：

Inception块：

1X1 convolution：信息融合（例子，分数之和决定排名），可以降低计算量

code：

self.branch1x1 = torch.nn.Conv2d(in_channels, 16, kernel_size=1)

InceptionA:

code:(不可单独运行)

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)

        barnch_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)

总的code：
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

batch_size = 64
transforms = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, )) # 第一个(0.1307, )是均值，第二个是标准差
])
train_dataset = datasets.MNIST(root=’…/dataset/mnist’,
train=True,
download=True,
transform=transforms)
train_loader = DataLoader(train_dataset,
shuffle=True,
batch_size=batch_size)

test_dataset = datasets.MNIST(root=’…/dataset/mnist’,
train=False,
download=True,
transform=transforms)
test_loader = DataLoader(test_dataset,
shuffle=False,
batch_size=batch_size)

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)

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)

    self.incep1 = InceptionA(in_channels=10)
    self.incep2 = InceptionA(in_channels=20)

    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()

if torch.cuda.is_available():
device = “cuda:0”
else:
device = “cpu”
device = torch.device(device)
model.to(device)

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

def train(epoch):
running_loss = 0.0
for batch_idx, data in enumerate(train_loader, 0):

X:inputs,Y:target

    inputs, target = data
    inputs, target = inputs.to(device), target.to(device)
    optimizer.zero_grad()

    # 前向+反向+更新
    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) # 算每一行最大值的下标是多少，其实也代表了每一行的分类 / max返回 每一行最大值是多少，每一行最大值的下标是多少
total += labels.size(0)
correct += (predicted == labels).sum().item() # ==预测的和原来的作比较，真为1，假为0，再总的加起来，求和后再把这个标量提出来
print(‘Accuracy on test set: %d %%’ % (100 * correct / total))

if name == ‘main’:
epoch_list = []
accuracy_list = []
for epoch in range(10):
train(epoch)
test()
效果图：

Residual Network:解决梯度消失，加了一个跳连接，H（x）= F（x）+ x，对x求导后，会有一个1,保证会大于1！

梯度消失指：
w -= a *g，当g小于0时，每一层都会乘一个小于0的数（g），这样久了后，w就不会再更新。

code:(不可单独运行)

class ResidualBlock(torch.nn.Module):
    def __init__(self, channels):
        super.channels = channels
        # 保证输入输出通道一样
        self.conv1 = torch.nn.Conv2d(channels, channels,
                               kernel_size=3, paddind=1)
        self.conv2 = torch.nn.Conv2d(channels, channels,
                               kernel_size=3, paddind=1)

    def forward(self, x):
        y = F.relu(self.conv1(x))
        y = self.conv2(y)
        return F.relu(x + y)

总的code：

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

batch_size = 64
transforms = transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.1307, ), (0.3081, )) # 第一个(0.1307, )是均值，第二个是标准差
])
train_dataset = datasets.MNIST(root='../dataset/mnist',
                               train=True,
                               download=True,
                               transform=transforms)
train_loader = DataLoader(train_dataset,
                          shuffle=True,
                          batch_size=batch_size)

test_dataset = datasets.MNIST(root='../dataset/mnist',
                              train=False,
                              download=True,
                              transform=transforms)
test_loader = DataLoader(test_dataset,
                         shuffle=False,
                         batch_size=batch_size)
class ResidualBlock(torch.nn.Module):
    def __init__(self, channels):
        super(ResidualBlock, self).__init__()
        self.channels = channels
        # 保证输入输出通道一样
        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)
        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)
        self.mp = torch.nn.MaxPool2d(2)

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

        self.fc = torch.nn.Linear(512, 10) # 线性层

    def forward(self, x):
        # 先求batch_size,用张量.size()求，取第0个，即是维度（样本的数量）
        # Flatten data from (n, 1, 28, 28) to (n, 784)
        batch_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(batch_size, -1) # flatten 平铺 # -1 此处自动算出的是320
        # print("x.shape",x.shape)
        x = self.fc(x)
        return x

model = Net()

# 使用GPU
if torch.cuda.is_available():
    device = "cuda:0"
else:
    device = "cpu"
device = torch.device(device)
model.to(device)

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

def train(epoch):
    running_loss = 0.0
    for batch_idx, data in enumerate(train_loader, 0):
#        X:inputs,Y:target
        inputs, target = data
        inputs, target = inputs.to(device), target.to(device)
        optimizer.zero_grad()

        # 前向+反向+更新
        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) # 算每一行最大值的下标是多少，其实也代表了每一行的分类 / max返回 每一行最大值是多少，每一行最大值的下标是多少
            total += labels.size(0)
            correct += (predicted == labels).sum().item() # ==预测的和原来的作比较，真为1，假为0，再总的加起来，求和后再把这个标量提出来
    print('Accuracy on test set: %d %%' % (100 * correct / total))

if __name__ == '__main__':
    epoch_list = []
    accuracy_list = []
    for epoch in range(10):
        train(epoch)
        test()

效果图：