一、前言
本篇记录自己常用到的小网络,分类简单的小图片时,可以获得较好的效果
二、代码
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(3, 6, 5, padding=2),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.layer2 = nn.Sequential(
nn.Conv2d(6, 12, kernel_size=5,padding=2),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.layer3 = nn.Sequential(
nn.Conv2d(12, 24, kernel_size=5,padding=2),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.layer4 = nn.Sequential(
nn.Conv2d(24, 36, kernel_size=5,padding=2),
nn.MaxPool2d(kernel_size=2, stride=2)
)
self.fc = nn.Sequential(
nn.Linear(36 * 3 * 3, 128),
nn.Dropout(0.2),
nn.ReLU(inplace=True),
nn.Linear(128, 64),
nn.Dropout(0.2),
nn.ReLU(inplace=True),
nn.Linear(64, 7) #注意这个最后的类别
)
def forward(self, x):
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
return x
class Net_2(nn.Module):
def __init__(self):
super(Net_2, self).__init__()
self.layer1 = nn.Sequential(
nn.Conv2d(1,16, 3, padding=1),
#nn.BatchNorm2d(16),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2) #16,48,16
)
self.layer2 = nn.Sequential(
nn.Conv2d(16, 32, kernel_size=3,padding=1),
#nn.BatchNorm2d(32),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2) #32,24,8
)
self.layer3 = nn.Sequential(
nn.Conv2d(32, 64, kernel_size=3,padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2) #64,12,4
)
self.layer4 = nn.Sequential(
nn.Conv2d(64, 128, kernel_size=3,padding=1),
nn.ReLU(inplace=True),
nn.MaxPool2d(kernel_size=2, stride=2) #128,6,2
)
self.fc1 = nn.Sequential(
nn.Linear(128 * 6 * 2, 256),
nn.Dropout(0.8),
nn.ReLU(inplace=True),
)
self.fc2 = nn.Sequential(
nn.Linear(256, 128),
nn.Dropout(0.8),
nn.ReLU(inplace=True),
)
self.fc = nn.Sequential(
nn.Linear(128, 2) #注意这个最后的类别
)
def forward(self, x):
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = x.view(x.size(0), -1)
x = self.fc1(x)
x = self.fc2(x)
x = self.fc(x)
return x
Net_1 参考lena-5, Net_2 使用CBRP经典结构,当然也可设计成全卷积分类网络,可支持不同大小输入