卷积神经网络
代码练习
一.MNIST数据集分类
1.加载数据（MNIST）
调用加载MNIST，为卷积神经网络准备好数据集
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
import matplotlib.pyplot as plt
import numpy
# 一个函数，用来计算模型中有多少参数
def get_n_params(model):
np=0
for p in list(model.parameters()):
np += p.nelement()
return np
# 使用GPU训练，可以在菜单 "代码执行工具" -> "更改运行时类型" 里进行设置
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
input_size = 28*28 # MNIST上的图像尺寸是 28x28
output_size = 10 # 类别为 0 到 9 的数字，因此为十类
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('./data', train=True, download=True,
transform=transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])),
batch_size=64, shuffle=True)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('./data', train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])),
batch_size=1000, shuffle=True)
plt.figure(figsize=(8, 5))
for i in range(20):
plt.subplot(4, 5, i + 1)
image, _ = train_loader.dataset.__getitem__(i)
plt.imshow(image.squeeze().numpy(),'gray')
plt.axis('off');
2.创建网络
2.1.定义网络
class FC2Layer(nn.Module):
def __init__(self, input_size, n_hidden, output_size):
# nn.Module子类的函数必须在构造函数中执行父类的构造函数
# 下式等价于nn.Module.__init__(self)
super(FC2Layer, self).__init__()
self.input_size = input_size
# 这里直接用 Sequential 就定义了网络，注意要和下面 CNN 的代码区分开
self.network = nn.Sequential(
nn.Linear(input_size, n_hidden),
nn.ReLU(),
nn.Linear(n_hidden, n_hidden),
nn.ReLU(),
nn.Linear(n_hidden, output_size),
nn.LogSoftmax(dim=1)
)
def forward(self, x):
# view一般出现在model类的forward函数中，用于改变输入或输出的形状
# x.view(-1, self.input_size) 的意思是多维的数据展成二维
# 代码指定二维数据的列数为 input_size=784，行数 -1 表示我们不想算，电脑会自己计算对应的数字
# 在 DataLoader 部分，我们可以看到 batch_size 是64，所以得到 x 的行数是64
# 大家可以加一行代码：print(x.cpu().numpy().shape)
# 训练过程中，就会看到 (64, 784) 的输出，和我们的预期是一致的
# forward 函数的作用是，指定网络的运行过程，这个全连接网络可能看不啥意义，
# 下面的CNN网络可以看出 forward 的作用。
x = x.view(-1, self.input_size)
return self.network(x)
class CNN(nn.Module):
def __init__(self, input_size, n_feature, output_size):
# 执行父类的构造函数，所有的网络都要这么写
super(CNN, self).__init__()
# 下面是网络里典型结构的一些定义，一般就是卷积和全连接
# 池化、ReLU一类的不用在这里定义
self.n_feature = n_feature
self.conv1 = nn.Conv2d(in_channels=1, out_channels=n_feature, kernel_size=5)
self.conv2 = nn.Conv2d(n_feature, n_feature, kernel_size=5)
self.fc1 = nn.Linear(n_feature*4*4, 50)
self.fc2 = nn.Linear(50, 10)
# 下面的 forward 函数，定义了网络的结构，按照一定顺序，把上面构建的一些结构组织起来
# 意思就是，conv1, conv2 等等的，可以多次重用
def forward(self, x, verbose=False):
x = self.conv1(x)
x = F.relu(x)
x = F.max_pool2d(x, kernel_size=2)
x = self.conv2(x)
x = F.relu(x)
x = F.max_pool2d(x, kernel_size=2)
x = x.view(-1, self.n_feature*4*4)
x = self.fc1(x)
x = F.relu(x)
x = self.fc2(x)
x = F.log_softmax(x, dim=1)
return x
2.2.定义训练和测试函数
# 训练函数
def train(model):
model.train()
# 主里从train_loader里，64个样本一个batch为单位提取样本进行训练
for batch_idx, (data, target) in enumerate(train_loader):
# 把数据送到GPU中
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % 100 == 0:
print('Train: [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
def test(model):
model.eval()
test_loss = 0
correct = 0
for data, target in test_loader:
# 把数据送到GPU中
data, target = data.to(device), target.to(device)
# 把数据送入模型，得到预测结果
output = model(data)
# 计算本次batch的损失，并加到 test_loss 中
test_loss += F.nll_loss(output, target, reduction='sum').item()
# get the index of the max log-probability，最后一层输出10个数，
# 值最大的那个即对应着分类结果，然后把分类结果保存在 pred 里
pred = output.data.max(1, keepdim=True)[1]
# 将 pred 与 target 相比，得到正确预测结果的数量，并加到 correct 中
# 这里需要注意一下 view_as ，意思是把 target 变成维度和 pred 一样的意思
correct += pred.eq(target.data.view_as(pred)).cpu().sum().item()
test_loss /= len(test_loader.dataset)
accuracy = 100. * correct / len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
accuracy))
3.网络训练
3.1.小型全连接网络
n_hidden = 8 # number of hidden units
model_fnn = FC2Layer(input_size, n_hidden, output_size)
model_fnn.to(device)
optimizer = optim.SGD(model_fnn.parameters(), lr=0.01, momentum=0.5)
print('Number of parameters: {}'.format(get_n_params(model_fnn)))
train(model_fnn)
test(model_fnn)
3.2.卷积神经网络
n_features = 6 # number of feature maps
model_cnn = CNN(input_size, n_features, output_size)
model_cnn.to(device)
optimizer = optim.SGD(model_cnn.parameters(), lr=0.01, momentum=0.5)
print('Number of parameters: {}'.format(get_n_params(model_cnn)))
train(model_cnn)
test(model_cnn)
通过比较发现，CNN的效果要明显优于全连接的网络结构。
3.3打乱像素顺序
3.3.1.打乱像素顺序
perm = torch.randperm(784)
plt.figure(figsize=(8, 4))
for i in range(10):
image, _ = train_loader.dataset.__getitem__(i)
# permute pixels
image_perm = image.view(-1, 28*28).clone()
image_perm = image_perm[:, perm]
image_perm = image_perm.view(-1, 1, 28, 28)
plt.subplot(4, 5, i + 1)
plt.imshow(image.squeeze().numpy(), 'gray')
plt.axis('off')
plt.subplot(4, 5, i + 11)
plt.imshow(image_perm.squeeze().numpy(), 'gray')
plt.axis('off')
3.3.2.重新定义训练与测试函数
# 对每个 batch 里的数据，打乱像素顺序的函数
def perm_pixel(data, perm):
# 转化为二维矩阵
data_new = data.view(-1, 28*28)
# 打乱像素顺序
data_new = data_new[:, perm]
# 恢复为原来4维的 tensor
data_new = data_new.view(-1, 1, 28, 28)
return data_new
# 训练函数
def train_perm(model, perm):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
# 像素打乱顺序
data = perm_pixel(data, perm)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % 100 == 0:
print('Train: [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
# 测试函数
def test_perm(model, perm):
model.eval()
test_loss = 0
correct = 0
for data, target in test_loader:
data, target = data.to(device), target.to(device)
# 像素打乱顺序
data = perm_pixel(data, perm)
output = model(data)
test_loss += F.nll_loss(output, target, reduction='sum').item()
pred = output.data.max(1, keepdim=True)[1]
correct += pred.eq(target.data.view_as(pred)).cpu().sum().item()
test_loss /= len(test_loader.dataset)
accuracy = 100. * correct / len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
accuracy))
3.3.3.重新训练
全连接网络：
卷积神经网络：
可见在处理打乱的像素时，CNN因为卷积和池化，反而不如全连接的神经网络。
二.CIFAR10数据集分类
1.加载数据集 定义网络、损失函数和优化器：
import torch
import torchvision
import torchvision.transforms as transforms
import matplotlib.pyplot as plt
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
# 使用GPU训练，可以在菜单 "代码执行工具" -> "更改运行时类型" 里进行设置
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
transform = transforms.Compose(
[transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
# 注意下面代码中：训练的 shuffle 是 True，测试的 shuffle 是 false
# 训练时可以打乱顺序增加多样性，测试是没有必要
trainset = torchvision.datasets.CIFAR10(root='./data', train=True,
download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=64,
shuffle=True, num_workers=2)
testset = torchvision.datasets.CIFAR10(root='./data', train=False,
download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=8,
shuffle=False, num_workers=2)
classes = ('plane', 'car', 'bird', 'cat',
'deer', 'dog', 'frog', 'horse', 'ship', 'truck')
# 定义网络，损失函数和优化器
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(3, 6, 5)
self.pool = nn.MaxPool2d(2, 2)
self.conv2 = nn.Conv2d(6, 16, 5)
self.fc1 = nn.Linear(16 * 5 * 5, 120)
self.fc2 = nn.Linear(120, 84)
self.fc3 = nn.Linear(84, 10)
def forward(self, x):
x = self.pool(F.relu(self.conv1(x)))
x = self.pool(F.relu(self.conv2(x)))
x = x.view(-1, 16 * 5 * 5)
x = F.relu(self.fc1(x))
x = F.relu(self.fc2(x))
x = self.fc3(x)
return x
# 网络放到GPU上
net = Net().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
2.训练网络
for epoch in range(10): # 重复多轮训练
for i, (inputs, labels) in enumerate(trainloader):
inputs = inputs.to(device)
labels = labels.to(device)
# 优化器梯度归零
optimizer.zero_grad()
# 正向传播 + 反向传播 + 优化
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# 输出统计信息
if i % 100 == 0:
print('Epoch: %d Minibatch: %5d loss: %.3f' %(epoch + 1, i + 1, loss.item()))
print('Finished Training')
3.测试网络
correct = 0
total = 0
for data in testloader:
images, labels = data
images, labels = images.to(device), labels.to(device)
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %d %%' % (
100 * correct / total))
可以看出，能识别出大部分的图片内容
三.使用VGG16对CIFAR10分类
VGG16拥有16层网络层次，目前仍有很多人在使用。
1.定义VGG网络
class VGG(nn.Module):
def __init__(self):
super(VGG, self).__init__()
self.cfg = [64, 'M', 128, 'M', 256, 256, 'M', 512, 512, 'M', 512, 512, 'M']
self.features = self._make_layers(self.cfg)
self.classifier = nn.Linear(512, 10)
def forward(self, x):
out = self.features(x)
out = out.view(out.size(0), -1)
out = self.classifier(out)
return out
def _make_layers(self, cfg):
layers = []
in_channels = 3
for x in cfg:
if x == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
layers += [nn.Conv2d(in_channels, x, kernel_size=3, padding=1),
nn.BatchNorm2d(x),
nn.ReLU(inplace=True)]
in_channels = x
layers += [nn.AvgPool2d(kernel_size=1, stride=1)]
return nn.Sequential(*layers)
# 网络放到GPU上
net = VGG().to(device)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)
2.网络训练测试
for epoch in range(10): # 重复多轮训练
for i, (inputs, labels) in enumerate(trainloader):
inputs = inputs.to(device)
labels = labels.to(device)
# 优化器梯度归零
optimizer.zero_grad()
# 正向传播 + 反向传播 + 优化
outputs = net(inputs)
loss = criterion(outputs, labels)
loss.backward()
optimizer.step()
# 输出统计信息
if i % 100 == 0:
print('Epoch: %d Minibatch: %5d loss: %.3f' %(epoch + 1, i + 1, loss.item()))
print('Finished Training')
运行时显示矩阵无法相乘，将之前self.classifier = nn.Linear(2048, 10) 改为self.classifier = nn.Linear(512, 10)解决问题
correct = 0
total = 0
for data in testloader:
images, labels = data
images, labels = images.to(device), labels.to(device)
outputs = net(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Accuracy of the network on the 10000 test images: %.2f %%' % (
100 * correct / total))
可以看到，使用了VGG16网络之后，准确率显著地提高了
浙公网安备 33010602011771号