Inceptionv1v2v3v4的pytorch实现

import torch import torch.nn as nn import torchvision def ConvBNReLU(in_channels,out_channels,kernel_size,stride=1,padding=0): return nn.Sequential( nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size, stride=stride,padding=padding), nn.BatchNorm2d(out_channels), nn.ReLU6(inplace=True), ) def ConvBNReLUFactorization(in_channels,out_channels,kernel_sizes,paddings): return nn.Sequential( nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_sizes, stride=1,padding=paddings), nn.BatchNorm2d(out_channels), nn.ReLU6(inplace=True) ) class InceptionV3ModuleA(nn.Module): def __init__(self, in_channels,out_channels1,out_channels2reduce, out_channels2, out_channels3reduce, out_channels3, out_channels4): super(InceptionV3ModuleA, self).__init__() self.branch1 = ConvBNReLU(in_channels=in_channels,out_channels=out_channels1,kernel_size=1) self.branch2 = nn.Sequential( ConvBNReLU(in_channels=in_channels, out_channels=out_channels2reduce, kernel_size=1), ConvBNReLU(in_channels=out_channels2reduce, out_channels=out_channels2, kernel_size=5, padding=2), ) self.branch3 = nn.Sequential( ConvBNReLU(in_channels=in_channels,out_channels=out_channels3reduce,kernel_size=1), ConvBNReLU(in_channels=out_channels3reduce, out_channels=out_channels3, kernel_size=3, padding=1), ConvBNReLU(in_channels=out_channels3, out_channels=out_channels3, kernel_size=3, padding=1), ) self.branch4 = nn.Sequential( nn.MaxPool2d(kernel_size=3, stride=1, padding=1), ConvBNReLU(in_channels=in_channels, out_channels=out_channels4, kernel_size=1), ) def forward(self, x): out1 = self.branch1(x) out2 = self.branch2(x) out3 = self.branch3(x) out4 = self.branch4(x) out = torch.cat([out1, out2, out3, out4], dim=1) return out class InceptionV3ModuleB(nn.Module): def __init__(self, in_channels,out_channels1,out_channels2reduce, out_channels2, out_channels3reduce, out_channels3, out_channels4): super(InceptionV3ModuleB, self).__init__() self.branch1 = ConvBNReLU(in_channels=in_channels,out_channels=out_channels1,kernel_size=1) self.branch2 = nn.Sequential( ConvBNReLU(in_channels=in_channels, out_channels=out_channels2reduce, kernel_size=1), ConvBNReLUFactorization(in_channels=out_channels2reduce, out_channels=out_channels2reduce, kernel_sizes=[1,7],paddings=[0,3]), ConvBNReLUFactorization(in_channels=out_channels2reduce, out_channels=out_channels2, kernel_sizes=[7,1],paddings=[3, 0]), ) self.branch3 = nn.Sequential( ConvBNReLU(in_channels=in_channels,out_channels=out_channels3reduce,kernel_size=1), ConvBNReLUFactorization(in_channels=out_channels3reduce, out_channels=out_channels3reduce,kernel_sizes=[1, 7], paddings=[0, 3]), ConvBNReLUFactorization(in_channels=out_channels3reduce, out_channels=out_channels3reduce,kernel_sizes=[7, 1], paddings=[3, 0]), ConvBNReLUFactorization(in_channels=out_channels3reduce, out_channels=out_channels3reduce,kernel_sizes=[1, 7], paddings=[0, 3]), ConvBNReLUFactorization(in_channels=out_channels3reduce, out_channels=out_channels3,kernel_sizes=[7, 1], paddings=[3, 0]), ) self.branch4 = nn.Sequential( nn.MaxPool2d(kernel_size=3, stride=1, padding=1), ConvBNReLU(in_channels=in_channels, out_channels=out_channels4, kernel_size=1), ) def forward(self, x): out1 = self.branch1(x) out2 = self.branch2(x) out3 = self.branch3(x) out4 = self.branch4(x) out = torch.cat([out1, out2, out3, out4], dim=1) return out class InceptionV3ModuleC(nn.Module): def __init__(self, in_channels,out_channels1,out_channels2reduce, out_channels2, out_channels3reduce, out_channels3, out_channels4): super(InceptionV3ModuleC, self).__init__() self.branch1 = ConvBNReLU(in_channels=in_channels,out_channels=out_channels1,kernel_size=1) self.branch2_conv1 = ConvBNReLU(in_channels=in_channels, out_channels=out_channels2reduce, kernel_size=1) self.branch2_conv2a = ConvBNReLUFactorization(in_channels=out_channels2reduce, out_channels=out_channels2, kernel_sizes=[1,3],paddings=[0,1]) self.branch2_conv2b = ConvBNReLUFactorization(in_channels=out_channels2reduce, out_channels=out_channels2, kernel_sizes=[3,1],paddings=[1, 0]) self.branch3_conv1 = ConvBNReLU(in_channels=in_channels,out_channels=out_channels3reduce,kernel_size=1) self.branch3_conv2 = ConvBNReLU(in_channels=out_channels3reduce, out_channels=out_channels3, kernel_size=3,stride=1,padding=1) self.branch3_conv3a = ConvBNReLUFactorization(in_channels=out_channels3, out_channels=out_channels3, kernel_sizes=[3, 1],paddings=[1, 0]) self.branch3_conv3b = ConvBNReLUFactorization(in_channels=out_channels3, out_channels=out_channels3, kernel_sizes=[1, 3],paddings=[0, 1]) self.branch4 = nn.Sequential( nn.MaxPool2d(kernel_size=3, stride=1, padding=1), ConvBNReLU(in_channels=in_channels, out_channels=out_channels4, kernel_size=1), ) def forward(self, x): out1 = self.branch1(x) x2 = self.branch2_conv1(x) out2 = torch.cat([self.branch2_conv2a(x2), self.branch2_conv2b(x2)],dim=1) x3 = self.branch3_conv2(self.branch3_conv1(x)) out3 = torch.cat([self.branch3_conv3a(x3), self.branch3_conv3b(x3)], dim=1) out4 = self.branch4(x) out = torch.cat([out1, out2, out3, out4], dim=1) return out class InceptionV3ModuleD(nn.Module): def __init__(self, in_channels,out_channels1reduce,out_channels1,out_channels2reduce, out_channels2): super(InceptionV3ModuleD, self).__init__() self.branch1 = nn.Sequential( ConvBNReLU(in_channels=in_channels, out_channels=out_channels1reduce, kernel_size=1), ConvBNReLU(in_channels=out_channels1reduce, out_channels=out_channels1, kernel_size=3,stride=2) ) self.branch2 = nn.Sequential( ConvBNReLU(in_channels=in_channels, out_channels=out_channels2reduce, kernel_size=1), ConvBNReLU(in_channels=out_channels2reduce, out_channels=out_channels2, kernel_size=3, stride=1, padding=1), ConvBNReLU(in_channels=out_channels2, out_channels=out_channels2, kernel_size=3, stride=2), ) self.branch3 = nn.MaxPool2d(kernel_size=3,stride=2) def forward(self, x): out1 = self.branch1(x) out2 = self.branch2(x) out3 = self.branch3(x) out = torch.cat([out1, out2, out3], dim=1) return out class InceptionV3ModuleE(nn.Module): def __init__(self, in_channels, out_channels1reduce,out_channels1, out_channels2reduce, out_channels2): super(InceptionV3ModuleE, self).__init__() self.branch1 = nn.Sequential( ConvBNReLU(in_channels=in_channels, out_channels=out_channels1reduce, kernel_size=1), ConvBNReLU(in_channels=out_channels1reduce, out_channels=out_channels1, kernel_size=3, stride=2), ) self.branch2 = nn.Sequential( ConvBNReLU(in_channels=in_channels, out_channels=out_channels2reduce, kernel_size=1), ConvBNReLUFactorization(in_channels=out_channels2reduce, out_channels=out_channels2reduce,kernel_sizes=[1, 7], paddings=[0, 3]), ConvBNReLUFactorization(in_channels=out_channels2reduce, out_channels=out_channels2reduce,kernel_sizes=[7, 1], paddings=[3, 0]), ConvBNReLU(in_channels=out_channels2reduce, out_channels=out_channels2, kernel_size=3, stride=2), ) self.branch3 = nn.MaxPool2d(kernel_size=3, stride=2) def forward(self, x): out1 = self.b