更新版yolov5_deepsort_pytorch实现目标检测和跟踪

由于mikel-brostrom在github上发布的Yolov5_DeepSort_Pytorch更新,使整个代码封装性更好,进而允许采用多种REID特征识别模型,完善了deepsort在检测跟踪方面的性能。本博文记录如何使用此版本Yolov5_DeepSort_Pytorch的过程,同时给出ZQPei REID模型的修改方法,以适应mikel-brostrom更新版本。

使用Yolov5_DeepSort_Pytorch默认的osnet REID实现跟踪track.py

Yolov5_DeepSort_Pytorch中包含了两个链接目录yolov5和reid,不能一次性把github中的代码克隆下来,因此,需分别将三个github代码克隆到本地。
Yolov5_DeepSort_Pytorch:git clone https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch
Yolov5:git clone https://github.com/ultralytics/yolov5
REID:git clone https://github.com/KaiyangZhou/deep-person-reid

假定你的deepsort目录为your_dir,是第一个克隆下来的目录。第二个克隆目录是yolov5,将yolov5目录放在your_dir目录下,即your_dir/yolov5。第三个克隆目录是reid,放到your_dir/deep_sort/deep目录下,your_dir/deep_sort/deep/reid。
假定已经安装了conda和虚拟环境,且安装好运行Yolov5_DeepSort_Pytorch所需的模块。进入reid目录,运行

python setup.py develop

如此,即安装好KaiyangZhou的REID环境。
下载yolov5模型权重,放入目录your_dir/yolov5/weights
从KaiyangZhou的github中,Model zoo里下载权重文件,例如osnet_x1_0.pth,放到checkpoint目录:your_dir/deep_sort/deep/checkpoint。

(1)修改deep_sort/configs/deep_sort.yaml

DEEPSORT:
  MODEL_TYPE: "osnet_x1_0"    
  REID_CKPT:  '~/your_dir/deep_sort/deep/checkpoint/osnet_x1_0_imagenet.pth'
  MAX_DIST: 0.1 # 0.2 The matching threshold. Samples with larger distance are considered an invalid match
  MAX_IOU_DISTANCE: 0.7 # 0.7 Gating threshold. Associations with cost larger than this value are disregarded.
  MAX_AGE: 90 # 30 Maximum number of missed misses before a track is deleted
  N_INIT: 3 # 3  Number of frames that a track remains in initialization phase
  NN_BUDGET: 100 # 100 Maximum size of the appearance descriptors gallery
  MIN_CONFIDENCE: 0.75
  NMS_MAX_OVERLAP: 1.0

这里,增加REID_CKPT,把某些参数设置放到yaml文件中,尽可能减少track.py命令行中的输入参数。

(2)修改track.py中DeepSort类实例的参数定义

deepsort = DeepSort(    cfg.DEEPSORT.MODEL_TYPE,
                        cfg.DEEPSORT.REID_CKPT,   # 添加checkpoint路径
                        device,
                        max_dist=cfg.DEEPSORT.MAX_DIST,
                        max_iou_distance=cfg.DEEPSORT.MAX_IOU_DISTANCE,
                        max_age=cfg.DEEPSORT.MAX_AGE, 
                        n_init=cfg.DEEPSORT.N_INIT, 
                        nn_budget=cfg.DEEPSORT.NN_BUDGET,
                        )

此处增加了一个reid权重文件路径参数,故也需在DeepSort类定义中增加该参数model_path,修改deep_sort/deep_sort.py,__init__():

class DeepSort(object):
    def __init__(self, model_type, model_path, device, max_dist=0.2, min_confidence=0.3, nms_max_overlap=1.0, max_iou_distance=0.7, max_age=70, n_init=3, nn_budget=100, use_cuda=True):
        self.min_confidence = min_confidence
        self.nms_max_overlap = nms_max_overlap
        self.extractor = FeatureExtractor(
            model_name=model_type,
            model_path = model_path,
            device=str(device)
        )
        max_cosine_distance = max_dist
        metric = NearestNeighborDistanceMetric(
            "cosine", max_cosine_distance, nn_budget)
        self.tracker = Tracker(
            metric, max_iou_distance=max_iou_distance, max_age=max_age, n_init=n_init)

注:mikel好像又改了有关model_path的引入方法,我感觉太复杂,故还是用以上的修改办法,其目的就是从deep_sort/deep/checkpoint中找到权重文件路径,避免从网上下载权重文件,或者从本地缓存.torch中去找权重。

(3)运行deepsort跟踪程序

python track.py --yolo_model ~/your_dir/yolov5/weights/yolov5s.pt \ 
                --source  ~/your_dir/video_demo.mp4 \          
                --show-vid \
                --classes 0

其中,classes 0 表示yolov5检测对象为行人,类型号0。

更改ZQPei REID模型文件

此模型文件命名为model_ZQP.py,放入目录 deep_sort/deep/reid/torchreid/models
模型更改只需添加一个定义函数 def ZQP()

import torch
import torch.nn as nn
import torch.nn.functional as F

class BasicBlock(nn.Module):
    def __init__(self, c_in, c_out, is_downsample=False):
        super(BasicBlock, self).__init__()
        self.is_downsample = is_downsample
        if is_downsample:
            self.conv1 = nn.Conv2d(
                c_in, c_out, 3, stride=2, padding=1, bias=False)
        else:
            self.conv1 = nn.Conv2d(
                c_in, c_out, 3, stride=1, padding=1, bias=False)
        self.bn1 = nn.BatchNorm2d(c_out)
        self.relu = nn.ReLU(True)
        self.conv2 = nn.Conv2d(c_out, c_out, 3, stride=1,
                               padding=1, bias=False)
        self.bn2 = nn.BatchNorm2d(c_out)
        if is_downsample:
            self.downsample = nn.Sequential(
                nn.Conv2d(c_in, c_out, 1, stride=2, bias=False),
                nn.BatchNorm2d(c_out)
            )
        elif c_in != c_out:
            self.downsample = nn.Sequential(
                nn.Conv2d(c_in, c_out, 1, stride=1, bias=False),
                nn.BatchNorm2d(c_out)
            )
            self.is_downsample = True

    def forward(self, x):
        y = self.conv1(x)
        y = self.bn1(y)
        y = self.relu(y)
        y = self.conv2(y)
        y = self.bn2(y)
        if self.is_downsample:
            x = self.downsample(x)
        return F.relu(x.add(y), True)

def make_layers(c_in, c_out, repeat_times, is_downsample=False):
    blocks = []
    for i in range(repeat_times):
        if i == 0:
            blocks += [BasicBlock(c_in, c_out, is_downsample=is_downsample), ]
        else:
            blocks += [BasicBlock(c_out, c_out), ]
    return nn.Sequential(*blocks)

class Net(nn.Module):             
    def __init__(self, num_classes=751, pretrained=True, loss = 'softmax', **kwargs):   # market1501=751, dukemtmcreid=702
        super(Net, self).__init__()   # Net
        # 3 128 64
        self.conv = nn.Sequential(
            nn.Conv2d(3, 64, 3, stride=1, padding=1),
            nn.BatchNorm2d(64),
            nn.ELU(inplace=True),
        )
        self.layer1 = make_layers(64, 64, 2, False)
        self.layer2 = make_layers(64, 128, 2, True)
        self.layer3 = make_layers(128, 256, 2, True)
        self.layer4 = make_layers(256, 512, 2, True)
        #self.avgpool = nn.AvgPool2d((8,4),1)
        self.adaptiveavgpool = nn.AdaptiveAvgPool2d(1)
        self.classifier = nn.Sequential(
            nn.Linear(512, 256),
            nn.BatchNorm1d(256),
            nn.ReLU(inplace=True),
            nn.Dropout(),
            nn.Linear(256, num_classes),
        )

    def forward(self, x):
        x = self.conv(x)
        x = self.layer1(x)
        x = self.layer2(x)
        x = self.layer3(x)
        x = self.layer4(x)
        #x = self.avgpool(x)
        x = self.adaptiveavgpool(x)   #
        x = x.view(x.size(0),-1)
        # B x 128
        if not self.training:
            x = x.div(x.norm(p=2,dim=1,keepdim=True))   
            return x
        # classifier
        x = self.classifier(x)
        return x

def ZQP(num_classes=751, pretrained=True, loss='softmax', **kwargs):
    model = Net(
        num_classes=num_classes, 
        pretrained = pretrained,
        loss = 'softmax',
        **kwargs
    )
    return model

if __name__ == '__main__':
    net = Net(pretrained=True)  # Net
    x = torch.randn(4, 3, 256, 256)  # 128, 64
    y = net(x)

下面将模型ZQP添加到REID的定义文件中
deep_sort/deep/reid/torchreid/models/__init__.py中引入ZQP模型文件,添加:

from .model_ZQP import *

在字典__model_factory中添加模型名称ZQP:

__model_factory = {
# image classification models
    'resnet18': resnet18,
    'resnet34': resnet34,
    'resnet50': resnet50,
......
    'ZQP': ZQP

现在,只要修改deep_sort/configs/deep_sort.yaml中的MODEL_TYPE和REID_CKPT路径,就可运行ZQPei的reid模型ckpt.t7。

  MODEL_TYPE: "ZQP"    
  REID_CKPT:  '~/your_dir/deep_sort/deep/checkpoint/ckpt.t7'

另外,由于ZQPei reid模型训练中resize为128×64(hxw),故需修改deep_sort/deep/reid/torchreid/utils/feature_extractor.py中的image_size

def __init__(
        self,
        model_name='',
        model_path='',
        image_size=(128, 64),           #(256, 128)  (h, w)
        pixel_mean=[0.485, 0.456, 0.406],
        pixel_std=[0.229, 0.224, 0.225],
        pixel_norm=True,
        device='cuda',
        verbose=True
    ):

至此,我们完成了添加ZQP reid模型到KaiyangZhou REID模型中的整个过程,并可以用同样的命令行参数,运行track.py

reid模型训练

deepsort中有两个神经网络模型,一个是目标检测模型yolov5,另一个是特征识别模型reid。yolov5模型训练有很多文章可参考,省略,此处侧重谈谈reid模型的训练。KaiyangZhou给出识别行人特征的reid模型训练方法,训练程序deep_sort/deep/reid/scripts/main.py。
训练可分别采用两个数据集:Market-1501和DukeMTMC-reID。
Market-1501数据集:
训练数据集”bounding_box_train“有751个行人ID,包含 12,936 张图像,平均每人有17.2张训练数据;
测试集“bounding_box_test”有750个行人ID,包含19,732张图像,平均每人有26.3张测试数据。
查询集gally从测试集中挑选出750个行人在6个摄像头下的图片,共3368 张查询图像。
dukemtmc-reid数据集:
“bounding_box_test”——用于测试集的 702 人,包含 17,661 张图像(随机采样,702 ID + 408 distractor ID)
“bounding_box_train”——用于训练集的 702 人,包含 16,522 张图像(随机采样)
“query”——为测试集中的 702 人在每个摄像头中随机选择一张图像作为 query,共有 2,228 张图像
只要从网上下载这两个数据集,不需要改变目录结构来使用它们排列的目录结构,只要指出数据集的根目录即可。
以下给出ZQPei模型在dukemtmc-reid数据集的训练方法
构造配置文件:deep_sort/deep/reid/configs/ZQP_128x64.yaml

model:
  name: 'ZQP'
  pretrained: True #True

data:
  type: 'image'
  sources: ['dukemtmcreid']
  targets: ['dukemtmcreid']       # market1501,  dukemtmcreid
  height: 128
  width: 64
  combineall: False
  transforms: ['random_flip']    #random_flip random_erase  color_jitter
  save_dir: 'deep_sort/deep/reid/log/ZQP'

loss:
  name: 'softmax'
  softmax:
    label_smooth: True

train:
  optim: 'amsgrad'
  lr: 0.0015
  max_epoch: 40  #150
  batch_size: 64
  fixbase_epoch: 10   #10
  open_layers: ['classifier']  #'classifier'
  lr_scheduler: 'cosine'
# stepsize: [60]

test:
  batch_size: 300
  dist_metric: 'euclidean'
  normalize_feature: False
  evaluate:  False  #test only
  eval_freq: -1
  rerank: False

运行训练程序main.py

python main.py \
    --config-file  deep_sort/deep/reid/configs/ZQP_128x64.yaml   \
    --root  ~/your_datasets/dukemtmc_reid   \
    model.load_weights ~/your_dir/deep_sort/deep/checkpoint/ckpt.t7

这里,在配置文件ZQP_128x64.yaml中pretrained = True,表示需加载预先训练的权重ckpt.t7。如果从头开始训练,则pretrained = False,并在命令行中删除model.load_weights项。命令行指定配置文件ZQP_128x64.yaml,数据集根目录dukemtmc_reid。
此外,采用dukemtmc训练数据集行人ID数为702,所以,需更改特征类型为702, 即模型文件model_ZQP.py中num_classes=702。

数据集目录组成应该是:
~/your_datasets/dukemtmc_reid/dukemtmc-reid/DukeMTMC-reID/bounding_box_test, bounding_box_train, query
用逗号分开的项目表示在DukeMTMC-reID目录下有三个子目录bounding_box_test、bounding_box_train和query。

用自己的数据集训练reid

要利用KaiyangZhou reid训练程序,需要将数据集构造成market-1501的结构形式,即bounding_box_train, bounding_box_test, guery。
下面是一个例子,用veri-wild提供的小汽车数据集来构造符合market-1501构成形式的数据集。
veri-wild提供了包含40多万张4万辆汽车的id图片,每个汽车ID目录下有多张不同摄像机和不同时刻获取的汽车图片。假定选择800个汽车ID组成训练集,另外800个汽车ID组成测试集,从测试集中取出每个汽车ID在每个摄像头下的图片,组成query。
(1)从veri-wild中分别抽取800个ID放入train_800和test_800,每个ID的图片在20-30张之间。
(2)对train_800和test_800图片进行resize,压缩数据集容量。
(3)按照market-1501文件命名规则更改数据集图片名称,并从test数据集挑选图片放入query。
由此,仿照market-1501构成训练reid的小汽车数据集,进行汽车特征的reid特征识别模型。

参考程序如下:

import os
from shutil import copyfile, copytree, rmtree
from torch.functional import broadcast_shapes
from PIL import Image
import matplotlib.pyplot as plt
import random
import shutil

def get_cam_n(f_list):      # 构造列表[file_name, camera_ID],列表抽取,每个camera_ID只取一项。
    A = []
    for cam_n in range(1,7):
        for j in range(len(f_list)):
            B = f_list[j][1] 
            if (f_list[j][1] == cam_n):
                A.append(f_list[j])
                break
    return A

def make_fileprefix(src_dir, tar_dir, gallary_dir):   # src_dir 带ID子目录的数据集目录,ID子目录下是同一ID的图片。
    for subdir in os.listdir( src_dir ):   # ID子目录名称
        src=src_dir+"/"+subdir
        f_list = []
        for file_name in os.listdir(src):  # 提取ID子目录内文件名称
            fileprefix= os.path.splitext(file_name)[0]
            cam_n = random.randint(1,6)
            A1=[fileprefix, cam_n]
            f_list.append(A1)
            file_name1 = subdir+ "_c"+str( cam_n) +"_f" +    fileprefix + ".jpg"
            copyfile(src+"/"+file_name, tar_dir+"/"+file_name1)  #将各子目录文件添加prefix,拷贝到一个目标文件夹tar_dir
            print("copyfile: ", file_name1)
        f_cam=get_cam_n(f_list)           # 列表[file_name, camera_ID],每个camera_ID只有一张图片。
        for i in range(len(f_cam)):       # 从 test中抽取图片到query
            file_prefix = f_cam[i][0]
            cam_n = f_cam[i][1]
            file_name1 = subdir+ "_c"+str( cam_n) +"_f" +    file_prefix + ".jpg"
            file_name0 = src+"/"+file_prefix+'.jpg'
            copyfile(file_name0, gallary_dir+"/"+file_name1)  #将各子目录文件添加prefix,拷贝到一个目标文件夹tar_dir
    return


def image_resize(src_dir, tar_dir):
    for subdir in os.listdir( src_dir ):   # ID子目录名称
        src=src_dir+"/"+subdir
        tar_ID_dir=tar_dir+"/"+subdir
        if  os.path.isdir(tar_ID_dir):
            rmtree(tar_ID_dir)
        os.mkdir(tar_ID_dir)
    
        for file_name in os.listdir(src):  # 提取ID子目录中文件名称
            img=Image.open(src+"/"+file_name)
            w, h =img.size
        #img.show()
            imax = max(h,w)
            if imax < 280:
                copyfile(src+"/"+file_name, tar_ID_dir+"/"+file_name)
            else:
                rate_hw = 280/imax
                w,h = int(rate_hw*w), int(rate_hw*h)
                new_img = img.resize((w, h),Image.BILINEAR)
            #new_img.show()
                new_img.save(tar_ID_dir+"/"+file_name)
            print(tar_ID_dir+"/"+file_name)
        return


if __name__ == '__main__':
    src_dir = "~/your_datasets/resize/train_800"
    tar_dir = "~/your_datasets/train_box"
    if  os.path.isdir(tar_dir):
        rmtree(tar_dir)
    os.mkdir(tar_dir)
    gallary_dir = "your_datasets/resize/gallary"
    if  os.path.isdir(gallary_dir):
        rmtree(gallary_dir)
    os.mkdir(gallary_dir)
    make_fileprefix(src_dir, tar_dir, gallary_dir)
    

文章出处登录后可见!

已经登录?立即刷新

共计人评分,平均

到目前为止还没有投票!成为第一位评论此文章。

(0)
扎眼的阳光的头像扎眼的阳光普通用户
上一篇 2022年3月31日 上午11:52
下一篇 2022年3月31日 下午12:05

相关推荐

此站出售,如需请站内私信或者邮箱!