我的孪生网络代码来源于孪生网络博主，这里的源代码使用的vgg16作为特征提取网络，我的主要工作是将vgg16替换为resnet网络。

1.建立resnet网络

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的主干网络搭建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：原论文中，在虚线残差结构的主分支上，第一个1x1卷积层的步距是2，第二个3x3卷积层步距是1。但在pytorch官方实现过程中是第一个1x1卷积层的步距是1，第二个3x3卷积层步距是2，这么做的好处是能够在top1上提升大概0.5%的准确率。可参考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.修改调用网络的siamese.py文件

修改的主要思路就是按照原来调用vgg16的思路，将调用vgg16的地方全部修改为调用resnet网络。这里可以修改为调用resnet34，resnet50和resnet101.

原来的调用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#------------------------------------------##   我们将两个输入传入到主干特征提取网络#------------------------------------------#x1 = self.vgg.features(x1)x2 = self.vgg.features(x2)   #-------------------------##   相减取绝对值#-------------------------#     x1 = torch.flatten(x1, 1)x2 = torch.flatten(x2, 1)x = torch.abs(x1 - x2)#-------------------------##   进行两次全连接#-------------------------#x = self.fully_connect1(x)x = self.fully_connect2(x)return x

修改后调用resnet网络的部分：这是调用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#------------------------------------------##   我们将两个输入传入到主干特征提取网络#------------------------------------------#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)#-------------------------##   相减取绝对值#-------------------------#     x1 = torch.flatten(x1, 1)x2 = torch.flatten(x2, 1)x = torch.abs(x1 - x2)#-------------------------##   进行两次全连接#-------------------------#x = self.fully_connect1(x)x = self.fully_connect2(x)return x

对于原文的：

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

我不是很明白它的长宽是怎么计算的，我就根据resnet50的输出关系，将其直接手动修改为512*4*4，在resnet50的特征提取的最后一个池化层之后的输出特征维度就是512*4*4，当然这是对对应105*105长宽输入图像的时候，如果要自己修改一个图像输入尺寸，只需要看看resnet最后一个池化层的输出特征维度即可。如果是resnet101，则需要将这部分改为2048*4*4.

对于特征提取部分，源码写的是：

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

如果我按照源码这样去写是这样的：

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

但是这样总是会报错，因此我就将特征提取部分改为这样：

        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)

对于最后的向量相似度计算：源码用的是相减的绝对值

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

我试过：

        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)

感觉结果都差不多。

孪生网络pytoch实现，以resnet为特征提取网络相关推荐

小白入门计算机视觉系列——ReID(二)：baseline构建：基于PyTorch的全局特征提取网络（Finetune ResNet50+tricks）
ReID(二):baseline构建:基于PyTorch的全局特征提取网络(Finetune ResNet50+tricks) 本次带来的是计算机视觉中比较热门的重点的一块,行人重识别(也叫Perso ...
yolov4源码_YOLOv4特征提取网络——CSPDarkNet结构解析及PyTorch实现
1 YOLOv4目标检测模型自从Redmon说他不在更新YOLO系列之后,我一度以为这么好用的框架就要慢慢淡入历史了,事实是我多虑了.YOLOv4在使用YOLO Loss的基础上,使用了新的back ...
【YOLOV4】(7) 特征提取网络代码复现（CSPDarknet53+SPP+PANet+Head），附Tensorflow完整代码
各位同学好,今天和大家分享一下如何使用 TensorFlow 构建YOLOV4目标检测算法的特征提取网络. 完整代码在我的Gitee中,有需要的自取:https://gitee.com/dgvv4/y ...
基于并行附加特征提取网络的SSD地面小目标检测模型
人工智能技术与咨询来源:<电子学报> ,作者李宝奇等摘要: 针对SSD原始附加特征提取网络(Original Additional Feature Extraction Networ ...
resnet结构_经典卷积网络（二）-ResNet
一.ResNet(总结自csdn文章) 随着网络的加深,出现了训练集准确率下降的现象,确定这不是由于Overfit过拟合造成的.作者针对这个问题提出了一种全新的网络,叫深度残差网络,它允许网络尽可能的 ...
ResNet深度残差网络
ResNet 论文:"Deep Residual Learning for Image Recognition" 面临的问题 ResNet解决的是深度神经网络的"退化&q ...
ResNet、ResNeXt网络详解及复现
网络详解: ResNet网络详解 ResNeXt网络详解 torch复现: import torch.nn as nn import torch''' 对应着18层和34层的残差结构既要拥有实现部分 ...
深度学习：ResNet（残差网络）
ResNet在ILSVRC2015竞赛中惊艳亮相,一下子将网络深度提升到152层,将错误率降到了3.57,在图像识别错误率和网络深度方面,比往届比赛有了非常大的提升,ResNet毫无悬念地夺得了ILS ...
深度学习笔记（七）--ResNet（残差网络）
内容来自吴恩达老师视频,网易云课堂有哦 ResNets 非常非常深的神经网络是很难训练的,因为存在梯度消失和梯度爆炸问题.ResNets是由残差块(Residual block)构建的,首先解释一下什 ...
非深度网络 Non-deep Network：低延迟平行网络 ParNet，仅 12 层媲美 ResNet
Non-deep Network Ankit Goyal1,2 Alexey Bochkovskiy2 Jia Deng1 Vladlen Koltun2 1Princeton Unive ...

孪生网络pytoch实现，以resnet为特征提取网络

1.建立resnet网络

2.修改调用网络的siamese.py文件

孪生网络pytoch实现，以resnet为特征提取网络相关推荐

最新文章

热门文章