CNN practice 2021-10-16

目录

• 代码练习
  • lab 1
    • 模型代码
    • 截图
  • lab2
    • 模型代码
    • 截图
  • lab3
    • 模型代码
    • 截图
• 想法解读

代码练习

lab 1

模型代码

class FC2Layer(nn.Module):
    def __init__(self, input_size, n_hidden, output_size):
        super(FC2Layer, self).__init__()
    	self.input_size = input_size
    	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):
    	x = x.view(-1, self.input_size)
    	return self.network(x)
    
    #生成实例
    model_fnn = FC2Layer(input_size, n_hidden, output_size)
	optimizer = optim.SGD(model_fnn.parameters(), lr=0.01, momentum=0.5)

 

class CNN(nn.Module):
    def __init__(self, input_size, n_feature, output_size):
        super(CNN, self).__init__()
        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)    
    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
    
    #生成实例
    model_cnn = CNN(input_size, n_features, output_size)
	optimizer = optim.SGD(model_cnn.parameters(), lr=0.01, momentum=0.5)

 

截图

 

 

 

 

 

 

lab2

 

模型代码

 

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
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)

 

截图

 

 

 

 

 

lab3

由于colab上跑的太慢，在本地跑了结果

 

模型代码

 

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)
criterion = nn.CrossEntropyLoss()
optimizer = optim.Adam(net.parameters(), lr=0.001)

 

截图

 

 

想法解读

相较于直白的全连接网络，CNN在图像处理领域有着压倒性的优势。一个好的模型往往离不开足够大的数据集。经典模型在一定广度上有着很好的表现。