系列文章目录

第一章目标检测与跟踪（1）- 机器人视觉与YOLO V8

目标检测与跟踪（1）- 机器人视觉与YOLO V8_Techblog of HaoWANG的博客-CSDN博客3D物体实时检测、三维目标识别、6D位姿估计一直是机器人视觉领域的核心研究课题，最新的研究成果也广泛应用于工业信息化领域的方方面面。通过众多的传感器，例如激光扫描仪、深度摄像头、双目视觉传感即可获得三维物体的识别数据，以此为基础开展研究的计算机视觉方向领域也有着较为深入的发展。https://blog.csdn.net/hhaowang/article/details/131893371?spm=1001.2014.3001.5501

2. 下载Pytorch &torchvision

前言

YOLOv8 算法的核心特性和改动可以归结为如下：

1. 提供了一个全新的 SOTA 模型，包括 P5 640 和 P6 1280 分辨率的目标检测网络和基于 YOLACT 的实例分割模型。和 YOLOv5 一样，基于缩放系数也提供了 N/S/M/L/X 尺度的不同大小模型，用于满足不同场景需求

2. Backbone:
骨干网络和 Neck 部分可能参考了 YOLOv7 ELAN 设计思想，将 YOLOv5 的 C3 结构换成了梯度流更丰富的 C2f 结构，并对不同尺度模型调整了不同的通道数。

在这里插入图片描述

YOLO timeline

一、安装CUDA&cuDNN

参考专题博客文章

Ubuntu 18.04/20.04 CV环境配置（上）：CUDA11.1 + cudnn安装配置_ubuntu安装cuda11.1_Techblog of HaoWANG的博客-CSDN博客Ubuntu18.04 20.04 NVIDIA CUDA 环境配置与cudnn Tensorrt等配置与使用_ubuntu安装cuda11.1https://blog.csdn.net/hhaowang/article/details/125803582?spm=1001.2014.3001.5501

二、安装Pytorch

1.安装miniconda

conda activate yolov8

2. 下载Pytorch &torchvision

在pytorch版本查询页面，查看与自己的NVIDA Version相匹配的安装指令，从中查看匹配的pytorch和torchvision的版本号

Previous PyTorch Versions | PyTorchAn open source machine learning framework that accelerates the path from research prototyping to production deployment.https://pytorch.org/get-started/previous-versions/

如下图所示可以看到Linux and Window环境下CUDA 11.1，所对应的pytorch版本是1.9.1，torchvision版本是0.10.1

进入pytorch官网安装页面，找到对应的pytorch和torchvision的安装包（cp代表python版本，如果其中一个文件找不到对应版本，则重复上一步骤查询可匹配的其他版本）

https://link.csdn.net/?target=https%3A%2F%2Fdownload.pytorch.org%2Fwhl%2Ftorch_stable.html

3. 安装

1. 激活配置环境，conda activate yolov8

2. 使用pip install进行配置

pip install torch-1.9.1+cu111-cp38-cp38-win_amd64.whl
pip install torchvision-0.10.1+cu111-cp38-cp38-win_amd64.whl

安装完成提示

Successfully installed certifi-2023.7.22 charset-normalizer-3.2.0 contourpy-1.1.0 cycler-0.11.0 fonttools-4.41.1 idna-3.4 importlib-resources-6.0.0 kiwisolver-1.4.4 matplotlib-3.7.2 opencv-python-4.8.0.74 packaging-23.1 pandas-2.0.3 psutil-5.9.5 py-cpuinfo-9.0.0 pyparsing-3.0.9 python-dateutil-2.8.2 pytz-2023.3 pyyaml-6.0.1 requests-2.31.0 scipy-1.10.1 seaborn-0.12.2 six-1.16.0 tqdm-4.65.0 tzdata-2023.3 ultralytics-8.0.146 urllib3-2.0.4 zipp-3.16.2

三、工程源码安装

源码GitHub地址：https://docs.ultralytics.com/quickstart/#install-ultralytics

https://docs.ultralytics.com/quickstart/#understanding-settings

1. 源码安装：

Clone the ultralytics repository if you are interested in contributing to the development or wish to experiment with the latest source code. After cloning, navigate into the directory and install the package in editable mode -e using pip.

# Clone the ultralytics repository
git clone https://github.com/ultralytics/ultralytics

# Navigate to the cloned directory
cd ultralytics

# Install the package in editable mode for development
pip install -e .

2. pip安装

Install the ultralytics package using pip, or update an existing installation by running pip install -U ultralytics. Visit the Python Package Index (PyPI) for more details on the ultralytics package: https://pypi.org/project/ultralytics/.

注意：conda先激活虚拟环境，再进行pip install步骤

# Install the ultralytics package using pip
pip install ultralytics

四、功能特性与测试

Ultralytics YOLOv8 Tasks - Ultralytics YOLOv8 Docs

Segment

Instance segmentation goes a step further than object detection and involves identifying individual objects in an image and segmenting them from the rest of the image.

The output of an instance segmentation model is a set of masks or contours that outline each object in the image, along with class labels and confidence scores for each object. Instance segmentation is useful when you need to know not only where objects are in an image, but also what their exact shape is.


YOLOv8 Segment models use the -seg suffix, i.e. yolov8n-seg.pt and are pretrained on COCO.

五、测试

Ultralytics YOLOv8 supports several modes that can be used to perform different tasks. These modes are:

Train: For training a YOLOv8 model on a custom dataset.
Val: For validating a YOLOv8 model after it has been trained.
Predict: For making predictions using a trained YOLOv8 model on new images or videos.
Export: For exporting a YOLOv8 model to a format that can be used for deployment.
Track: For tracking objects in real-time using a YOLOv8 model.
Benchmark: For benchmarking YOLOv8 exports (ONNX, TensorRT, etc.) speed and accuracy.

CLI - Ultralytics YOLOv8 DocsLearn how to use Ultralytics YOLO through Command Line: train models, run predictions and exports models to different formats easily using terminal commands.https://docs.ultralytics.com/usage/cli/

yolo使用命令行（CLI）执行操作，进入虚拟环境后按照 yolo TASK MODE ARGS指令形式。

参数解释如下：

 yolo TASK MODE ARGS

      Where   TASK (optional) is one of ('detect', 'segment', 'classify', 'pose')
              MODE (required) is one of ('train', 'val', 'predict', 'export', 'track', 'benchmark')
              ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults.
                    See all ARGS at https://docs.ultralytics.com/usage/cfg or with 'yolo cfg'

使用预训练模型进行测试：

yolo detect predict model=yolov8n-seg.pt source='https://ultralytics.com/images/bus.jpg'

执行单一图片的分割预测，使用预训练模型yolov8n-seg.pt

注意：LooseVersion = distutils.version.LooseVersion报错

修改miniconda3/envs/yolov8/lib/python3.8/site-packages/torch/utils/tensorboard/__init__.py

import tensorboard
#from setuptools import distutils
from distutils.version import LooseVersion

# LooseVersion = distutils.version.LooseVersion

if not hasattr(tensorboard, '__version__') or LooseVersion(tensorboard.__version__) < LooseVersion('1.15'):
    raise ImportError('TensorBoard logging requires TensorBoard version 1.15 or above')

#del distutils
del LooseVersion
del tensorboard

from .writer import FileWriter, SummaryWriter  # noqa: F401
from tensorboard.summary.writer.record_writer import RecordWriter  # noqa: F401