Pytorch---CNN

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：

https://github.com/yunjey/pytorch-tutorial/blob/master/tutorials/02intermediate/convolutional_neural_network/main.py#L35-L56

pytorch 中文文档

李宏毅-Convolutional Neural Network（CNN）-卷积神经网络