# 卷积神经网络（高级篇）《PyTorch深度学习实践》

1.Inception Module

1*1卷积核：输入不同通道相同位置的信息的融合

``````import torch
import torch.nn as nn
from torchvision import transforms
from torchvision import datasets
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

# 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]

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

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
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

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）

``````import torch
import torch.nn as nn
from torchvision import transforms
from torchvision import datasets
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

# 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

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
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