行人重识别模型搭建与训练

1、参考论文

Bag of Tricks and A Strong Baseline for Deep Person Re-identification

2、模型结构

ResNet有2个基本的block，一个是Identity Block，输入和输出的dimension是一样的，所以可以串联多个；另外一个基本block是Conv Block，输入和输出的dimension是不一样的，所以不能连续串联，它的作用本来就是为了改变特征向量的dimension

                                                                                   图1. Resnet50网络的结构

其中，resnet50网络中的Conv Block和ID Block如图2、图3所示。

 

                                                                                     图2. Conv Block结构示意图

                                                                                      图3. ID Block结构示意图

3、使用pytorch搭建Resnet网络

resnet.py如下所示：

# encoding: utf-8
"""
@author:  liaoxingyu
@contact: sherlockliao01@gmail.com
"""

import math

import torch
from torch import nn


def conv3x3(in_planes, out_planes, stride=1):
    """3x3 convolution with padding"""
    return nn.Conv2d(in_planes, out_planes, kernel_size=3, stride=stride,
                     padding=1, bias=False)


class BasicBlock(nn.Module):
    expansion = 1

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(BasicBlock, self).__init__()
        self.conv1 = conv3x3(inplanes, planes, stride)
        self.bn1 = nn.BatchNorm2d(planes)
        self.relu = nn.ReLU(inplace=True)
        self.conv2 = conv3x3(planes, planes)
        self.bn2 = nn.BatchNorm2d(planes)
        self.downsample = downsample
        self.stride = stride

    def forward(self, x):
        residual = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            residual = self.downsample(x)

        out += residual
        out = self.relu(out)

        return out


class Bottleneck(nn.Module):
    expansion = 4

    def __init__(self, inplanes, planes, stride=1, downsample=None):
        super(Bottleneck, self).__init__()
        self.conv1 = nn.Conv2d(inplanes, planes, kernel_size=1, bias=False)
        self.bn1 = nn.BatchNorm2d(planes)
        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride,
                               padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(planes)
        self.conv3 = nn.Conv2d(planes, planes * 4, kernel_size=1, bias=False)
        self.bn3 = nn.BatchNorm2d(planes * 4)
        self.relu = nn.ReLU(inplace=True)