CNN网络输入层、隐藏层(卷积层和池化层)、输出层。卷积神经网络的特殊性体现在两个方面,一方面是神经元之间的连接不是全连接,另一方面是同一层中某些神经元之间的权重值是共享的。因此学习CNN主要是学习卷积层和池化层。
1.学习CNN 神经网络首先得知道卷积的原理:
1 | 1 | 1 | 1 |
0 | 0 | 1 | 1 |
0 | 1 | 1 | 0 |
0 | 1 | 1 | 0 |
卷积
1 | 1 |
0 | 1 |
结果为:
2 | 3 | 3 |
1 | 2 | 2 |
2 | 3 | 1 |
卷积的原理就是与原来的位置一一对应,然后结果相加既可。比如上面卷积的结果就是4*4的矩阵,结果成为了3*3的矩阵。
此处有定则:假设上一层图大小是n*n,卷积核大小是k*k,则卷积后该层图的大小则是(n-k+1)*(n-k+1).
另外需要记住的参数是padding是补0用的,stride是步长。
2.CNN层的池化层
池化层的输入一般来源于上一个卷积层,主要作用是提供很强的鲁棒性并且减少参数的量,防止过拟合的现象发生。
1 | 1 | 2 | 4 |
5 | 6 | 7 | 8 |
3 | 2 | 1 | 0 |
1 | 2 | 3 | 4 |
经过maxpool 2*2 filters 和stride=2,则结果为:
6 | 8 |
3 | 4 |
3. 看得视频:
三大特性: Property1 ,Property2, Property3.
第四代码:
import torch
import torch.nn as nn
import torchvision
import torchvision.transforms as transforms
# Device configuration
device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
# Hyper parameters
num_epochs = 5
num_classes = 10
batch_size = 100
learning_rate = 0.001
# MNIST dataset
train_dataset = torchvision.datasets.MNIST(root='../../data/',
train=True,
transform=transforms.ToTensor(),
download=True)
test_dataset = torchvision.datasets.MNIST(root='../../data/',
train=False,
transform=transforms.ToTensor())
# Data loader
train_loader = torch.utils.data.DataLoader(dataset=train_dataset,
batch_size=batch_size,
shuffle=True)
test_loader = torch.utils.data.DataLoader(dataset=test_dataset,
batch_size=batch_size,
shuffle=False)
# Convolutional neural network (two convolutional layers)
class ConvNet(nn.Module):
def __init__(self, num_classes=10):
super(ConvNet, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2), ## 16 是自己设置得
nn.BatchNorm2d(16),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=5, stride=1, padding=2),
nn.BatchNorm2d(32),
nn.ReLU(),
nn.MaxPool2d(kernel_size=2, stride=2))
self.fc = nn.Linear(7*7*32, num_classes)
def forward(self, x):
out = self.layer1(x)
out = self.layer2(out)
out = out.reshape(out.size(0), -1)
out = self.fc(out)
return out
model = ConvNet(num_classes).to(device)
# Loss and optimizer
criterion = nn.CrossEntropyLoss()
optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)
# Train the model
total_step = len(train_loader)
for epoch in range(num_epochs):
for i, (images, labels) in enumerate(train_loader):
images = images.to(device)
labels = labels.to(device)
# Forward pass
outputs = model(images)
loss = criterion(outputs, labels)
# Backward and optimize
optimizer.zero_grad()
loss.backward()
optimizer.step()
if (i+1) % 100 == 0:
print ('Epoch [{}/{}], Step [{}/{}], Loss: {:.4f}'
.format(epoch+1, num_epochs, i+1, total_step, loss.item()))
# Test the model
model.eval() # eval mode (batchnorm uses moving mean/variance instead of mini-batch mean/variance)
with torch.no_grad():
correct = 0
total = 0
for images, labels in test_loader:
images = images.to(device)
labels = labels.to(device)
outputs = model(images)
_, predicted = torch.max(outputs.data, 1)
total += labels.size(0)
correct += (predicted == labels).sum().item()
print('Test Accuracy of the model on the 10000 test images: {} %'.format(100 * correct / total))
# Save the model checkpoint
torch.save(model.state_dict(), 'model.ckpt')
© 2019 GitHub, Inc.
padding 通常是补0,也不会增加噪声。
参考:
李宏毅-Convolutional Neural Network(CNN)-卷积神经网络