《PyTorch深度学习实践》课上代码笔记 五
自学笔记
课程老师：刘二大人 河北工业大学教师 https://liuii.github.io
课程来源：https://www.bilibili.com/video/BV1Y7411d7Ys
十二、Residual_Block（残差网络）
为了防止梯度的消失，在一定次数的卷积操作后(一般为两次)，将结果与输入进行相加后进行relu，这样后的梯度最小会在1左右，而不是0，能有效避免梯度消失。残差部分的代码如下：
#定义残差块
class ResidualBlock(nn.Module):
def __init__(self, channels):
super(ResidualBlock, self).__init__()
#初始化属性
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)
#定义前馈函数
def forward(self, x):
y = F.relu(self.conv1(x))
y = self.conv2(y)
#返回值为输入x + y(经过处理的x)
return F.relu(x + y)
将残差块按需要放在整个网络中，即可构成一个完整的网络。
#设计模型
class Net(nn.Module):
#初始化属性
def __init__(self):
super(Net, self).__init__()
#两个卷积
self.conv1 = nn.Conv2d(1, 16, kernel_size=5)
self.conv2 = nn.Conv2d(16, 32, kernel_size=5)
#最大池化
self.mp = nn.MaxPool2d(2)
#两个残差块
self.rblock1 = ResidualBlock(16)
self.rblock2 = ResidualBlock(32)
#全连接
self.fc = nn.Linear(512, 10)
def forward(self, x):
#这里是提取了x的行数,可以理解为输入数据的个数,x.size(1)为列，及数据维度
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)
#将x从(banch,32,4,4)变为(in_size,512),in_size即banch大小
x = x.view(in_size, -1)
x = self.fc(x)
return x
整体代码如下：
#导入相应的包
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
import torch.nn as nn
#小训练集大小
batch_size = 64
#数据集的处理
#图片变换:转换成Tensor,标准化
transform = transforms.Compose([transforms.ToTensor(),
transforms.Normalize((0.1307,),(0.3081,))])
#创建训练数据集
train_dataset = datasets.MNIST(root='../dataset/mnist/',
train=True, download=True,
transform=transform)
#导入训练数据集
train_loader = DataLoader(train_dataset,
shuffle=True,
batch_size=batch_size)
#创建测试数据集
test_dataset = datasets.MNIST(root='../dataset/mnist/',
train=False,
download=True,
transform=transform)
#导入测试数据集
test_loader = DataLoader(test_dataset,
shuffle=False,
batch_size=batch_size)
#定义残差块
class ResidualBlock(nn.Module):
def __init__(self, channels):
super(ResidualBlock, self).__init__()
#初始化属性
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)
#定义前馈函数
def forward(self, x):
y = F.relu(self.conv1(x))
y = self.conv2(y)
#返回值为输入x + y(经过处理的x)
return F.relu(x + y)
#设计模型
class Net(nn.Module):
#初始化属性
def __init__(self):
super(Net, self).__init__()
#两个卷积
self.conv1 = nn.Conv2d(1, 16, kernel_size=5)
self.conv2 = nn.Conv2d(16, 32, kernel_size=5)
#最大池化
self.mp = nn.MaxPool2d(2)
#两个残差块
self.rblock1 = ResidualBlock(16)
self.rblock2 = ResidualBlock(32)
#全连接
self.fc = nn.Linear(512, 10)
def forward(self, x):
#这里是提取了x的行数,可以理解为输入数据的个数,x.size(1)为列，及数据维度
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)
#将x从(banch,32,4,4)变为(in_size,512),in_size即banch大小
x = x.view(in_size, -1)
x = self.fc(x)
return x
#实例化
model = Net()
#损失函数及反馈
criterion = torch.nn.CrossEntropyLoss()
optimizer = optim.SGD(model.parameters(), lr=0.01, momentum=0.5)
#训练
def train(epoch):
running_loss = 0.0
for batch_idx,data in enumerate(train_loader, 0):
inputs, target = data
optimizer.zero_grad()
# forward + backward + update
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
#不计算梯度，节省内存
with torch.no_grad():
for data in test_loader:
#导入测试数据
images, labels = data
#带入模型，得到输出
outputs = model(images)
#找到输出中概率最大的下标及值
_, predicted = torch.max(outputs.data, dim=1)
#计算所有的测试个数
total += labels.size(0)
#计算正确的个数
correct += (predicted == labels).sum().item()
#输出准确率
print('Accuracy on test set: %d %%' % (100 * correct / total))
if __name__ == '__main__':
#训练10次
for epoch in range(10):
#训练
train(epoch)
#测试
test()