技术标签: yolov5 Deepsort 深度学习 目标跟踪
项目源码
pytorch yolo5+Deepsort实现目标检测和跟踪
YoloV5 + deepsort + Fast-ReID 完整行人重识别系统(三)
yolov5-deepsort-pedestrian-counting
Yolov5-Deepsort-Fastreid
Deepsort是实现目标跟踪的算法,从sort(simple online and realtime tracking)演变而来。其使用卡尔慢滤波器预测所检测对象的运动轨迹,匈牙利算法将它们与新检测的目标匹配。Deepsort易于使用,且速度快,成为AI目标检测跟踪的热门算法。
yolov5可检测多种类型的目标,而Deepsort目标跟踪只能跟踪一种类型目标,例如person、car。所以,跟踪需要把yolov5的目标检测类型数量限制成单个类型检测。coco数据集定义:person=0,car=2。
# 行人跟踪
python track.py --classes 0 --source demo_person.mp4
# 小汽车跟踪
python track.py --classes 2 --source demo_car.mp4
yolov5提供不同检测精度的权重文件,yolov5x.pt比yolov5s.pt精度高。应用跟踪时,当两个目标重叠后再分离,yolov5s.pt会出现标注数改变。比如,目标10和目标20发生重叠分离,目标10变成了目标15,而目标20不变(目标20遮挡目标10)。此种情况,用yolov5x.pt会好很多,维持目标10不变。
yolov5限定单个类型,不需要重新训练。faster rcnn、ResNet限定单个类型,单需要重新训练。
yolov5的速度明显优于FastRCNN,且消耗GPU资源少。用FastRCNN,还没用到Deepsort,只看逐帧检测,速度比yolov5+Deepsort逐帧目标检测还要慢,且GPU使用率达到95%。
yolov5的训练速度比Faster RCNN、ResNet50、FPN快。
Environment
Operating System + Version: Ubuntu + 16.04
GPU Type: GeForce GTX1650,4GB
Nvidia Driver Version: 470.63.01
CUDA Version: 10.2.300
CUDNN Version: 7.6.5
Python Version (if applicable): 3.6.14
virtualenv:20.13.0
gcc:7.5.0
g++:7.5.0
absl-py==1.0.0
cached-property==1.5.2
cachetools==4.2.4
certifi==2021.10.8
charset-normalizer==2.0.10
cycler==0.11.0
Cython==0.29.26
dataclasses==0.8
distlib==0.3.4
easydict==1.9
filelock==3.4.1
flake8==4.0.1
future==0.18.2
gdown==3.10.1
google-auth==2.3.3
google-auth-oauthlib==0.4.6
grpcio==1.43.0
h5py==3.1.0
idna==3.3
imageio==2.13.5
importlib-metadata==4.2.0
importlib-resources==5.4.0
isort==4.3.21
kiwisolver==1.3.1
Markdown==3.3.5
matplotlib==3.3.4
mccabe==0.6.1
numpy==1.19.5
oauthlib==3.1.1
opencv-python==4.5.5.62
pandas==1.1.5
Pillow==8.4.0
platformdirs==2.4.0
protobuf==3.19.3
pyasn1==0.4.8
pyasn1-modules==0.2.8
pycodestyle==2.8.0
pyflakes==2.4.0
pyparsing==3.0.6
PySocks==1.7.1
python-dateutil==2.8.2
pytz==2021.3
PyYAML==6.0
requests==2.27.1
requests-oauthlib==1.3.0
rsa==4.8
scipy==1.5.4
seaborn==0.11.2
six==1.16.0
tb-nightly==2.8.0a20220117
tensorboard-data-server==0.6.1
tensorboard-plugin-wit==1.8.1
torch==1.9.0+cu102
torchvision=0.10.0+cu102
tqdm==4.62.3
typing_extensions==4.0.1
urllib3==1.26.8
virtualenv==20.13.0
Werkzeug==2.0.2
yacs==0.1.8
yapf==0.32.0
zipp==3.6.0
git clone https://github.com/mikel-brostrom/Yolov5_DeepSort_Pytorch.git
.
├── deep_sort
│ ├── configs
│ ├── deep
│ ├── deep_sort.py
│ ├── __init__.py
│ ├── LICENSE
│ ├── __pycache__
│ ├── README.md
│ ├── sort
│ └── utils
├── inference # infer 推理的结果
│ └── output
├── LICENSE
├── MOT16_eval
│ ├── eval.sh
│ ├── track_all.gif
│ └── track_pedestrians.gif
├── README.md
├── requirementes-gpu.txt
├── requirements.txt
├── runs
│ └── track
├── track.py
├── venv # virtualenv 创建的虚拟环境
│ ├── bin
│ ├── lib
│ └── pyvenv.cfg
├── yolov5 # clone yolov5 to this path
│ ├── CONTRIBUTING.md
│ ├── data
│ ├── detect.py
│ ├── Dockerfile
│ ├── export.py
│ ├── hubconf.py
│ ├── LICENSE
│ ├── models
│ ├── README.md
│ ├── requirements.txt
│ ├── setup.cfg
│ ├── train.py
│ ├── tutorial.ipynb
│ ├── utils
│ ├── val.py
│ └── weights
下载到 Yolov5_DeepSort_Pytorch
根目录下,删除之前的yolov5文件夹。
git clone https://github.com/ultralytics/yolov5.git
deep-person-reid
改为
reid
# 进入项目路径
cd Yolov5_DeepSort_Pytorch
# 创建虚拟环境
virtualenv --system-site-packages -p /usr/bin/python venv
# 激活虚拟环境
source ./venv/bin/activate
# 安装依赖包
pip install -r requirements.txt
选择目标检测模型:yolov5;
选择DeepSort模型:ReID;
下载地址,并放入目录 Yolov5_DeepSort_Pytorchyolo5/weights
比如, yolov5s.pt
python track.py --source 0 --yolo_model yolov5/weights/yolov5n.pt --img 640
yolov5/weights/yolov5s.pt
yolov5/weights/yolov5m.pt
yolov5/weights/yolov5l.pt
yolov5/weights/yolov5x.pt --img 1280
...
下载地址,放入目录 Yolov5_DeepSort_Pytorch/deep_sort_pytorch/deep_sort/deep/checkpoint
比如,osnet_x1_0
python track.py --source 0 --deep_sort_model osnet_x1_0
nasnsetmobile
resnext101_32x8d
python track.py --source 0 --yolo_model yolov5/weights/yolov5n.pt --deep_sort_model osnet_x1_0 --img 640
(venv) yichao@yichao:~/MyDocuments/Yolov5_DeepSort_Pytorch$ python track.py --source 0 --yolo_model yolov5/weights/yolov5s.pt --deep_sort_model osnet_x1_0 --img 640
deep_sort/deep/reid/torchreid/metrics/rank.py:12: UserWarning: Cython evaluation (very fast so highly recommended) is unavailable, now use python evaluation.
'Cython evaluation (very fast so highly recommended) is '
Successfully loaded imagenet pretrained weights from "/home/yichao/MyDocuments/Yolov5_DeepSort_Pytorch/deep_sort/deep/checkpoint/osnet_x1_0_imagenet.pth"
Selected model type: osnet_x1_0
YOLOv5 v6.0-193-gdb1f83b torch 1.9.0+cu102 CUDA:0 (NVIDIA GeForce GTX 1650, 3904MiB)
YOLOv5 v6.0-193-gdb1f83b torch 1.9.0+cu102 CUDA:0 (NVIDIA GeForce GTX 1650, 3904MiB)
weight_path: yolov5/weights/yolov5s.pt
weight_path: yolov5/weights/yolov5s.pt
Fusing layers...
Model Summary: 224 layers, 7266973 parameters, 0 gradients
1/1: 0... Success (inf frames 640x480 at 30.00 FPS)
0: 480x640 1 person, Done. YOLO:(0.428s), DeepSort:(0.220s)
0: 480x640 1 person, Done. YOLO:(0.023s), DeepSort:(0.020s)
0: 480x640 1 person, Done. YOLO:(0.010s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
...
...
...
由于预训练模型是手动下载的,所以需要修改源码中的路径。
修改 osnet_ain.py
源码
# 源码路径
Yolov5_DeepSort_Pytorch/deep_sort/deep/reid/torchreid/models/osnet.py
cached_file = os.path.join(model_dir, filename)
改为
cached_file = "/home/yichao/MyDocuments/Yolov5_DeepSort_Pytorch/deep_sort/deep/checkpoint/osnet_x1_0_imagenet.pth"
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.010s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.010s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.011s), DeepSort:(0.013s)
0: 480x640 1 person, Done. YOLO:(0.010s), DeepSort:(0.013s)
# yolov5+Deepsort,大约24ms,即41FPS
# DeepSort 的速度取决于画面中目标的数目,上述数据是在单目标的情况下进行统计的。
Tue Jan 18 16:06:27 2022
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 470.63.01 Driver Version: 470.63.01 CUDA Version: 11.4 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|===============================+======================+======================|
| 0 NVIDIA GeForce ... Off | 00000000:01:00.0 On | N/A |
| 27% 43C P0 44W / 75W | 1895MiB / 3903MiB | 79% Default |
| | | N/A |
+-------------------------------+----------------------+----------------------+
+-----------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=============================================================================|
| 0 N/A N/A 1529 G /usr/lib/xorg/Xorg 218MiB |
| 0 N/A N/A 5928 C python 1673MiB |
+-----------------------------------------------------------------------------+
YoloV5+DeepSort+TensorRT 目标检测、跟踪
yolov5_deepsort_tensorrt_cpp
_bz2
文件 File "/usr/local/lib/python3.6/bz2.py", line 23, in <module>
from _bz2 import BZ2Compressor, BZ2Decompressor
ModuleNotFoundError: No module named '_bz2'
错误原因:
缺少 _bz2.cpython-36m-x86_64-linux-gnu.so 文件
解决办法:
把系统自带Python3.6的“_bz2.cpython-36m-x86_64-linux-gnu.so”文件,放到Python3.8的文件夹中。
如果是Python3.8版本,也可以把文件改名后,放到Python3.6的文件夹中。
sudo cp /home/yichao/miniconda3/envs/compress_model/lib/python3.6/lib-dynload/_bz2.cpython-36m-x86_64-linux-gnu.so /usr/local/lib/python3.6/lib-dynload/
DetectMultiBackend
Traceback (most recent call last):
File "track.py", line 24, in <module>
from yolov5.models.common import DetectMultiBackend
ImportError: cannot import name 'DetectMultiBackend'
错误原因:
博主使用的不是最新版本的yolov5,且使用的分支是v5.0,yolov5/models/common文件中暂不支持DetectMultiBackend。
解决办法:
下载最新版本的yolov5,切换到最新的分支v6.0。
git clone https://github.com/ultralytics/yolov5.git
git checkout -b 新分支名称(创建) tag_name
File "./yolov5/models/yolo.py", line 222, in fuse
m.conv = fuse_conv_and_bn(m.conv, m.bn) # update conv
File "./yolov5/utils/torch_utils.py", line 207, in fuse_conv_and_bn
fusedconv.weight.copy_(torch.mm(w_bn, w_conv).view(fusedconv.weight.shape))
RuntimeError: CUDA error: CUBLAS_STATUS_INTERNAL_ERROR when calling `cublasCreate(handle)`
错误原因:
pytorch的版本问题,博主由于粗心,安装了CPU版本的Pytorch和pytorchvision。
torch-1.8.0-cp36-cp36m-linux_x86_64.whl
torchvision-0.9.0-cp36-cp36m-linux_x86_64.whl
解决办法:
安装GPU版本的pytorch和pytorchvison。
torch-1.9.0+cu102-cp36-cp36m-linux_x86_64.whl
torchvision-0.10.0+cu102-cp36-cp36m-linux_x86_64.whl
pytorch与pytorchvision版本对齐,参考 [Pytorch安装教程](https://blog.csdn.net/m0_37605642/article/details/117855911)
File "/home/yichao/MyDocuments/Yolov5_DeepSort_Pytorch/venv/lib/python3.6/site-packages/torchvision/extension.py", line 63, in _assert_has_ops
"Couldn't load custom C++ ops. This can happen if your PyTorch and "
RuntimeError: Couldn't load custom C++ ops. This can happen if your PyTorch and torchvision versions are incompatible, or if you had errors while compiling torchvision from source. For further information on the compatible versions, check https://github.com/pytorch/vision#installation for the compatibility matrix. Please check your PyTorch version with torch.__version__ and your torchvision version with torchvision.__version__ and verify if they are compatible, and if not please reinstall torchvision so that it matches your PyTorch install.
错误原因:
博主由于粗心,安装了cpu版本的torchvision,与GPU版本的pytorch不匹配。
torchvision-0.10.0-cp36-cp36m-linux_x86_64.whl
解决办法:
卸载pytorchvision,安装GPU版本的pytorchvison。
torchvision-0.10.0+cu102-cp36-cp36m-linux_x86_64.whl
文章浏览阅读290次,点赞8次,收藏10次。1.背景介绍稀疏编码是一种用于处理稀疏数据的编码技术,其主要应用于信息传输、存储和处理等领域。稀疏数据是指数据中大部分元素为零或近似于零的数据,例如文本、图像、音频、视频等。稀疏编码的核心思想是将稀疏数据表示为非零元素和它们对应的位置信息,从而减少存储空间和计算复杂度。稀疏编码的研究起源于1990年代,随着大数据时代的到来,稀疏编码技术的应用范围和影响力不断扩大。目前,稀疏编码已经成为计算...
文章浏览阅读217次。EasyGBS - GB28181 国标方案安装使用文档下载安装包下载,正式使用需商业授权, 功能一致在线演示在线API架构图EasySIPCMSSIP 中心信令服务, 单节点, 自带一个 Redis Server, 随 EasySIPCMS 自启动, 不需要手动运行EasySIPSMSSIP 流媒体服务, 根..._easygbs-windows-2.6.0-23042316使用文档
文章浏览阅读1.2k次,点赞27次,收藏7次。2023巅峰极客 BabyURL之前AliyunCTF Bypassit I这题考查了这样一条链子:其实就是Jackson的原生反序列化利用今天复现的这题也是大同小异,一起来整一下。_原生jackson 反序列化链子
文章浏览阅读734次,点赞9次,收藏7次。微服务架构简单的说就是将单体应用进一步拆分,拆分成更小的服务,每个服务都是一个可以独立运行的项目。这么多小服务,如何管理他们?(服务治理 注册中心[服务注册 发现 剔除])这么多小服务,他们之间如何通讯?这么多小服务,客户端怎么访问他们?(网关)这么多小服务,一旦出现问题了,应该如何自处理?(容错)这么多小服务,一旦出现问题了,应该如何排错?(链路追踪)对于上面的问题,是任何一个微服务设计者都不能绕过去的,因此大部分的微服务产品都针对每一个问题提供了相应的组件来解决它们。_spring cloud
文章浏览阅读5.9k次,点赞6次,收藏20次。Js实现图片点击切换与轮播图片点击切换<!DOCTYPE html><html> <head> <meta charset="UTF-8"> <title></title> <script type="text/ja..._点击图片进行轮播图切换
文章浏览阅读10w+次,点赞245次,收藏1.5k次。在开始安装前,如果你的电脑装过tensorflow,请先把他们卸载干净,包括依赖的包(tensorflow-estimator、tensorboard、tensorflow、keras-applications、keras-preprocessing),不然后续安装了tensorflow-gpu可能会出现找不到cuda的问题。cuda、cudnn。..._tensorflow gpu版本安装
文章浏览阅读243次。0x00 简介权限滥用漏洞一般归类于逻辑问题,是指服务端功能开放过多或权限限制不严格,导致攻击者可以通过直接或间接调用的方式达到攻击效果。随着物联网时代的到来,这种漏洞已经屡见不鲜,各种漏洞组合利用也是千奇百怪、五花八门,这里总结漏洞是为了更好地应对和预防,如有不妥之处还请业内人士多多指教。0x01 背景2014年4月,在比特币飞涨的时代某网站曾经..._使用物联网漏洞的使用者
文章浏览阅读786次。A. Epipolar geometry and triangulationThe epipolar geometry mainly adopts the feature point method, such as SIFT, SURF and ORB, etc. to obtain the feature points corresponding to two frames of images. As shown in Figure 1, let the first image be and th_normalized plane coordinates
文章浏览阅读708次,点赞2次,收藏3次。开放信息抽取(OIE)系统(三)-- 第二代开放信息抽取系统(人工规则, rule-based, 先关系再实体)一.第二代开放信息抽取系统背景 第一代开放信息抽取系统(Open Information Extraction, OIE, learning-based, 自学习, 先抽取实体)通常抽取大量冗余信息,为了消除这些冗余信息,诞生了第二代开放信息抽取系统。二.第二代开放信息抽取系统历史第二代开放信息抽取系统着眼于解决第一代系统的三大问题: 大量非信息性提取(即省略关键信息的提取)、_语义角色增强的关系抽取
文章浏览阅读1.1w次,点赞6次,收藏51次。快速完成网页设计,10个顶尖响应式HTML5网页模板助你一臂之力为了寻找一个优质的网页模板,网页设计师和开发者往往可能会花上大半天的时间。不过幸运的是,现在的网页设计师和开发人员已经开始共享HTML5,Bootstrap和CSS3中的免费网页模板资源。鉴于网站模板的灵活性和强大的功能,现在广大设计师和开发者对html5网站的实际需求日益增长。为了造福大众,Mockplus的小伙伴整理了2018年最..._html欢迎页面
文章浏览阅读282次。原标题:2018全国计算机等级考试调整,一、二级都增加了考试科目全国计算机等级考试将于9月15-17日举行。在备考的最后冲刺阶段,小编为大家整理了今年新公布的全国计算机等级考试调整方案,希望对备考的小伙伴有所帮助,快随小编往下看吧!从2018年3月开始,全国计算机等级考试实施2018版考试大纲,并按新体系开考各个考试级别。具体调整内容如下:一、考试级别及科目1.一级新增“网络安全素质教育”科目(代..._计算机二级增报科目什么意思
文章浏览阅读240次。conan简单使用。_apt install conan