Inception-v1实现

 Inception-v1中使用了多个11卷积核，其作用：
(1)在大小相同的感受野上叠加更多的卷积核，可以让模型学习到更加丰富的特征。传统的卷积层的输入数据只和一种尺寸的卷积核进行运算，而Inception-v1结构是Network in Network(NIN)，就是先进行一次普通的卷积运算(比如55)，经过激活函数(比如ReLU)输出之后，然后再进行一次11的卷积运算，这个后面也跟着一个激活函数。11的卷积操作可以理解为feature maps个神经元都进行了一个全连接运算。
(2)使用1*1的卷积核可以对模型进行降维，减少运算量。当一个卷积层输入了很多feature maps的时候，这个时候进行卷积运算计算量会非常大，如果先对输入进行降维操作，feature maps减少之后再进行卷积运算，运算量会大幅减少。

import torch
import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
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)

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()
 
# 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()

Skip Connect实现

 跳连结构解决了梯度消失的问题

import torch
import torch
from torchvision import transforms
from torchvision import datasets
from torch.utils.data import DataLoader
import torch.nn.functional as F
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)

class ResidualBlock (torch.nn.Module):
  def __init__(self, channels):
    super (ResidualBlock, self).__init__()
    self.channels = channels
    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.rblock1 = ResidualBlock(16)
    self.rblock2 = ResidualBlock(32)

    self.mp = torch.nn.MaxPool2d (2)
    self.fc = torch.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 = torch.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()