我的孿生網絡代碼來源于孿生網絡博主，這里的源代碼使用的vgg16作為特征提取網絡，我的主要工作是將vgg16替換為resnet網絡。

1.建立resnet網絡

import torch.nn as nn import torch # from torchvision.models.utils import load_state_dict_from_url from torchsummary import summary from torch.hub import load_state_dict_from_urlclass BasicBlock(nn.Module):#resnet18和resnet34的主干網絡搭建expansion = 1def __init__(self, in_channel, out_channel, stride=1, downsample=None, **kwargs):super(BasicBlock, self).__init__()self.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=out_channel,kernel_size=3, stride=stride, padding=1, bias=False)self.bn1 = nn.BatchNorm2d(out_channel)self.relu = nn.ReLU()self.conv2 = nn.Conv2d(in_channels=out_channel, out_channels=out_channel,kernel_size=3, stride=1, padding=1, bias=False)self.bn2 = nn.BatchNorm2d(out_channel)self.downsample = downsampledef forward(self, x):identity = xif self.downsample is not None:identity = self.downsample(x)out = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)out += identityout = self.relu(out)return outclass Bottleneck(nn.Module):"""注意：原論文中，在虛線殘差結構的主分支上，第一個1x1卷積層的步距是2，第二個3x3卷積層步距是1。但在pytorch官方實現過程中是第一個1x1卷積層的步距是1，第二個3x3卷積層步距是2，這么做的好處是能夠在top1上提升大概0.5%的準確率。可參考Resnet v1.5 https://ngc.nvidia.com/catalog/model-scripts/nvidia:resnet_50_v1_5_for_pytorch"""expansion = 4def __init__(self, in_channel, out_channel, stride=1, downsample=None,groups=1, width_per_group=64):super(Bottleneck, self).__init__()width = int(out_channel * (width_per_group / 64.)) * groupsself.conv1 = nn.Conv2d(in_channels=in_channel, out_channels=width,kernel_size=1, stride=1, bias=False) # squeeze channelsself.bn1 = nn.BatchNorm2d(width)# -----------------------------------------self.conv2 = nn.Conv2d(in_channels=width, out_channels=width, groups=groups,kernel_size=3, stride=stride, bias=False, padding=1)self.bn2 = nn.BatchNorm2d(width)# -----------------------------------------self.conv3 = nn.Conv2d(in_channels=width, out_channels=out_channel*self.expansion,kernel_size=1, stride=1, bias=False) # unsqueeze channelsself.bn3 = nn.BatchNorm2d(out_channel*self.expansion)self.relu = nn.ReLU(inplace=True)self.downsample = downsampledef forward(self, x):identity = xif self.downsample is not None:identity = self.downsample(x)out = self.conv1(x)out = self.bn1(out)out = self.relu(out)out = self.conv2(out)out = self.bn2(out)out = self.relu(out)out = self.conv3(out)out = self.bn3(out)out += identityout = self.relu(out)return outclass ResNet(nn.Module):def __init__(self,block,blocks_num,num_classes=1000,include_top=True,groups=1,width_per_group=64):super(ResNet, self).__init__()self.include_top = include_topself.in_channel = 64self.groups = groupsself.width_per_group = width_per_groupself.conv1 = nn.Conv2d(3, self.in_channel, kernel_size=7, stride=2,padding=3, bias=False)self.bn1 = nn.BatchNorm2d(self.in_channel)self.relu = nn.ReLU(inplace=True)self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)self.layer1 = self._make_layer(block, 64, blocks_num[0])self.layer2 = self._make_layer(block, 128, blocks_num[1], stride=2)self.layer3 = self._make_layer(block, 256, blocks_num[2], stride=2)self.layer4 = self._make_layer(block, 512, blocks_num[3], stride=2)if self.include_top:self.avgpool = nn.AdaptiveAvgPool2d((1, 1)) # output size = (1, 1)self.fc = nn.Linear(512 * block.expansion, num_classes)for m in self.modules():if isinstance(m, nn.Conv2d):nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')def _make_layer(self, block, channel, block_num, stride=1):downsample = Noneif stride != 1 or self.in_channel != channel * block.expansion:downsample = nn.Sequential(nn.Conv2d(self.in_channel, channel * block.expansion, kernel_size=1, stride=stride, bias=False),nn.BatchNorm2d(channel * block.expansion))layers = []layers.append(block(self.in_channel,channel,downsample=downsample,stride=stride,groups=self.groups,width_per_group=self.width_per_group))self.in_channel = channel * block.expansionfor _ in range(1, block_num):layers.append(block(self.in_channel,channel,groups=self.groups,width_per_group=self.width_per_group))return nn.Sequential(*layers)def forward(self, x):x = self.conv1(x)x = self.bn1(x)x = self.relu(x)x = self.maxpool(x)x = self.layer1(x)x = self.layer2(x)x = self.layer3(x)x = self.layer4(x)if self.include_top:x = self.avgpool(x)x = torch.flatten(x, 1)x = self.fc(x)return xdef resnet34(pretrained,num_classes=1000, include_top=True):# https://download.pytorch.org/models/resnet34-333f7ec4.pthmodel = ResNet(BasicBlock, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)if pretrained:state_dict = load_state_dict_from_url("https://download.pytorch.org/models/resnet34-333f7ec4.pth",model_dir="./model_data")model.load_state_dict(state_dict)return modeldef resnet50(pretrained,num_classes=1000, include_top=True):# https://download.pytorch.org/models/resnet50-19c8e357.pthmodel=ResNet(Bottleneck, [3, 4, 6, 3], num_classes=num_classes, include_top=include_top)if pretrained:state_dict = load_state_dict_from_url("https://download.pytorch.org/models/resnet50-19c8e357.pth",model_dir="./model_data")model.load_state_dict(state_dict)return modeldef resnet101(pretrained,num_classes=1000, include_top=True):# https://download.pytorch.org/models/resnet101-5d3b4d8f.pthmodel=ResNet(Bottleneck, [3, 4, 23, 3], num_classes=num_classes, include_top=include_top)if pretrained:state_dict = load_state_dict_from_url("https://download.pytorch.org/models/resnet101-5d3b4d8f.pth",model_dir="./model_data")model.load_state_dict(state_dict)return modeldef resnext50_32x4d(num_classes=1000, include_top=True):# https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pthgroups = 32width_per_group = 4return ResNet(Bottleneck, [3, 4, 6, 3],num_classes=num_classes,include_top=include_top,groups=groups,width_per_group=width_per_group)def resnext101_32x8d(num_classes=1000, include_top=True):# https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pthgroups = 32width_per_group = 8return ResNet(Bottleneck, [3, 4, 23, 3],num_classes=num_classes,include_top=include_top,groups=groups,width_per_group=width_per_group)if __name__=='__main__':net=resnet101(False)# del net.avgpoolsummary(net,(3,105,105))x=torch.rand(1,3,105,105)out=net(x)print(out.shape)

2.修改調用網絡的siamese.py文件

修改的主要思路就是按照原來調用vgg16的思路，將調用vgg16的地方全部修改為調用resnet網絡。這里可以修改為調用resnet34，resnet50和resnet101.

原來的調用vgg16部分：

class Siamese(nn.Module):def __init__(self, input_shape, pretrained=False):super(Siamese, self).__init__()self.vgg = VGG16(pretrained, input_shape[-1])del self.vgg.avgpooldel self.vgg.classifierflat_shape = 512 * get_img_output_length(input_shape[1], input_shape[0])self.fully_connect1 = torch.nn.Linear(flat_shape, 512)self.fully_connect2 = torch.nn.Linear(512, 1)def forward(self, x):x1, x2 = x#------------------------------------------## 我們將兩個輸入傳入到主干特征提取網絡#------------------------------------------#x1 = self.vgg.features(x1)x2 = self.vgg.features(x2) #-------------------------## 相減取絕對值#-------------------------# x1 = torch.flatten(x1, 1)x2 = torch.flatten(x2, 1)x = torch.abs(x1 - x2)#-------------------------## 進行兩次全連接#-------------------------#x = self.fully_connect1(x)x = self.fully_connect2(x)return x

修改后調用resnet網絡的部分：這是調用resnet50的修改部分。

class Siamese(nn.Module):def __init__(self, input_shape, pretrained=False):super(Siamese, self).__init__()self.resnet= resnet50(pretrained, include_top=True)del self.resnet.avgpooldel self.resnet.fc# flat_shape = 512 * get_img_output_length(input_shape[1], input_shape[0])flat_shape = 2048 * 4*4self.fully_connect1 = torch.nn.Linear(flat_shape, 512)self.fully_connect2 = torch.nn.Linear(512, 1)def forward(self, x):x1, x2 = x#------------------------------------------## 我們將兩個輸入傳入到主干特征提取網絡#------------------------------------------#x1 = self.resnet.conv1(x1)x1 = self.resnet.bn1(x1)x1 = self.resnet.relu(x1)x1 = self.resnet.maxpool(x1)x1 = self.resnet.layer1(x1)x1 = self.resnet.layer2(x1)x1 = self.resnet.layer3(x1)x1 = self.resnet.layer4(x1)x2 = self.resnet.conv1(x2)x2 = self.resnet.bn1(x2)x2 = self.resnet.relu(x2)x2 = self.resnet.maxpool(x2)x2 = self.resnet.layer1(x2)x2 = self.resnet.layer2(x2)x2 = self.resnet.layer3(x2)x2 = self.resnet.layer4(x2)#-------------------------## 相減取絕對值#-------------------------# x1 = torch.flatten(x1, 1)x2 = torch.flatten(x2, 1)x = torch.abs(x1 - x2)#-------------------------## 進行兩次全連接#-------------------------#x = self.fully_connect1(x)x = self.fully_connect2(x)return x

對于原文的：

flat_shape = 512 * get_img_output_length(input_shape[1], input_shape[0])

我不是很明白它的長寬是怎么計算的，我就根據resnet50的輸出關系，將其直接手動修改為512*4*4，在resnet50的特征提取的最后一個池化層之后的輸出特征維度就是512*4*4，當然這是對對應105*105長寬輸入圖像的時候，如果要自己修改一個圖像輸入尺寸，只需要看看resnet最后一個池化層的輸出特征維度即可。如果是resnet101，則需要將這部分改為2048*4*4.

對于特征提取部分，源碼寫的是：

x1 = self.vgg.features(x1) x2 = self.vgg.features(x2)

如果我按照源碼這樣去寫是這樣的：

x1 = self.resnet(x1) x2 = self.resnet(x2)

但是這樣總是會報錯，因此我就將特征提取部分改為這樣：

x1 = self.resnet.conv1(x1)x1 = self.resnet.bn1(x1)x1 = self.resnet.relu(x1)x1 = self.resnet.maxpool(x1)x1 = self.resnet.layer1(x1)x1 = self.resnet.layer2(x1)x1 = self.resnet.layer3(x1)x1 = self.resnet.layer4(x1)x2 = self.resnet.conv1(x2)x2 = self.resnet.bn1(x2)x2 = self.resnet.relu(x2)x2 = self.resnet.maxpool(x2)x2 = self.resnet.layer1(x2)x2 = self.resnet.layer2(x2)x2 = self.resnet.layer3(x2)x2 = self.resnet.layer4(x2)

對于最后的向量相似度計算：源碼用的是相減的絕對值

x1 = torch.flatten(x1, 1)x2 = torch.flatten(x2, 1)x = torch.abs(x1 - x2)

我試過：

x1 = torch.flatten(x1, 1)x2 = torch.flatten(x2, 1)x = torch.abs((x1 - x2)**2) x1 = torch.flatten(x1, 1)x2 = torch.flatten(x2, 1)x = torch.abs(x1*x1 - x2*x2) x1 = torch.flatten(x1, 1)x2 = torch.flatten(x2, 1)x = torch.abs((x1*x1 - x2*x2)**2)

感覺結果都差不多。

總結

以上是生活随笔為你收集整理的孪生网络pytoch实现，以resnet为特征提取网络的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。