PyTorch深度学习实践11——卷积神经网络高级
GoogleNet
- 减少代码冗余的思想：在面向过程的编程语言中体现为函数；在面向对象的编程语言中体现为类
- 1x1卷积核的作用
- concatenate操作
- 如何确定输出张量的尺寸：在定义时先不定义fc层，随便选取一个输入，经过模型后查看其尺寸
在本例中，init函数中把fc层去掉，forward函数中把最后两行去掉，确定输出的尺寸后再定义Lear层的大小
ResNet
- 为什么网络层数更深反而效果更差：
- 梯度消失：在反向传播时需要根据链式法则把一连串的梯度乘起来，若每个梯度都小于1，则乘起来的结果会接近于0，导致权重在更新时得不到什么更新，进而导致最开始的这些块（离输入近的块）没办法得到充分的训练。
- 梯度消失和梯度爆炸
- Residual block：偏导数大于1，不会出现梯度消失
- Resnet中为什么有虚线的跳连接？因为输入到该块的张量大小和输出的张量大小不一致，需要做特殊处理
- residual block的实现：
老师的期待：
学完本课程之后：
- 读读深度学习的花书，夯实理论基础
- 通读一遍PyTorch官方文档，知道提供了什么功能以及文档结构
- 复现经典工作（读代码=》写代码=》读代码=》...循环往复）
- 扩充视野，广泛阅读自己领域内的工作，看看别人的工作有没有自己不会复现的块
GoogleNet中Inception块的实现：
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
import time
import matplotlib.pyplot as plt
# prepare dataset
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)
# design model using class
class InceptionA(nn.Module):
def __init__(self, in_channels):
super(InceptionA, self).__init__()
self.branchx1 = 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.branchx1(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)
output = [branch1x1, branch5x5, branch3x3, branch_pool]
return torch.cat(output, 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)
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)
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()
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
model.to(device)
# 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
inputs, target = inputs.to(device), target.to(device)
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
accuracy = []
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)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('accuracy on test set: %d %% ' % (100 * correct / total))
accuracy.append(100* correct / total)
if __name__ == '__main__':
torch.cuda.synchronize()
start = time.time()
for epoch in range(10):
train(epoch)
test()
torch.cuda.synchronize()
end = time.time()
time_elapsed = end - start
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
# Training complete in 2m 44s
plt.plot(range(10), accuracy)
plt.xlabel("epoch")
plt.ylabel("accuracy")
plt.grid()
plt.show()
print("done")ResNet中residual block的实现：
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
import time
import matplotlib.pyplot as plt
# prepare dataset
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)
# 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)
self.conv2 = 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(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.mp = nn.MaxPool2d(2)
self.rblock1 = ResidualBlock(16)
self.rblock2 = ResidualBlock(32)
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()
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
model.to(device)
# 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
inputs, target = inputs.to(device), target.to(device)
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
accuracy = []
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)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('accuracy on test set: %d %% ' % (100 * correct / total))
accuracy.append(100 * correct / total)
if __name__ == '__main__':
torch.cuda.synchronize()
start = time.time()
for epoch in range(10):
train(epoch)
test()
torch.cuda.synchronize()
end = time.time()
time_elapsed = end - start
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
# Training complete in 2m 44s
plt.plot(range(10), accuracy)
plt.xlabel("epoch")
plt.ylabel("accuracy")
plt.grid()
plt.show()
print("done")课后作业一：实现constant scaling
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
import time
import matplotlib.pyplot as plt
# prepare dataset
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)
# 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)
self.conv2 = nn.Conv2d(channels, channels,
kernel_size=3, padding=1)
def forward(self, x):
y = F.relu(self.conv1(x))
y = self.conv2(x)
z = 0.5 * (x + y)
return F.relu(z)
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.mp = nn.MaxPool2d(2)
self.rblock1 = ResidualBlock(16)
self.rblock2 = ResidualBlock(32)
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()
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
model.to(device)
# 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
inputs, target = inputs.to(device), target.to(device)
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
accuracy = []
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)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('accuracy on test set: %d %% ' % (100 * correct / total))
accuracy.append(100 * correct / total)
if __name__ == '__main__':
torch.cuda.synchronize()
start = time.time()
for epoch in range(10):
train(epoch)
test()
torch.cuda.synchronize()
end = time.time()
time_elapsed = end - start
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
# Training complete in 2m 44s
plt.plot(range(10), accuracy)
plt.xlabel("epoch")
plt.ylabel("accuracy")
plt.grid()
plt.show()
print("done")课后作业2：实现conv shortcut
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
import time
import matplotlib.pyplot as plt
# prepare dataset
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)
# 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)
self.conv2 = nn.Conv2d(channels, channels,
kernel_size=3, padding=1)
self.conv3 = nn.Conv2d(channels, channels,
kernel_size=1)
def forward(self, x):
y = F.relu(self.conv1(x))
y = self.conv2(x)
z = self.conv3(x) + y
return F.relu(z)
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.mp = nn.MaxPool2d(2)
self.rblock1 = ResidualBlock(16)
self.rblock2 = ResidualBlock(32)
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()
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
model.to(device)
# 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
inputs, target = inputs.to(device), target.to(device)
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
accuracy = []
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)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('accuracy on test set: %d %% ' % (100 * correct / total))
accuracy.append(100 * correct / total)
if __name__ == '__main__':
torch.cuda.synchronize()
start = time.time()
for epoch in range(10):
train(epoch)
test()
torch.cuda.synchronize()
end = time.time()
time_elapsed = end - start
print('Training complete in {:.0f}m {:.0f}s'.format(
time_elapsed // 60, time_elapsed % 60))
# Training complete in 2m 44s
plt.plot(range(10), accuracy)
plt.xlabel("epoch")
plt.ylabel("accuracy")
plt.grid()
plt.show()
print("done")