Data

Tools

Indexes

Applications

Experiments

Open Source Science

yolov5_zz

https://github.com/wudixiaozhu123/yolov5_zz

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (4.0%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: wudixiaozhu123
  • License: agpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 1.17 MB
Statistics
  • Stars: 3
  • Watchers: 1
  • Forks: 0
  • Open Issues: 4
  • Releases: 0
Created about 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme Contributing License Citation

README.md

yolov5s应用于CIFAR10分类任务

目录

思路及安装

首先，思路是:yolov5s网络是有3个检测头的，分别对应小-中-大物体的检测然后再结合特征
而我们知道CIFAR10数据集是32×32的，那么显然，如果要把他应用到yolov5中，删除中，大头，保留小头是一个好的选择。

这边再提一下改进，下面简要陈列一下：
1.对于检测部分，我改进了其yolo.py中的Detect类，删除掉了makegrid方法，此方法用于生成 YOLO 等目标检测模型中的"网格"和"锚框"网格的工具函数。
其作用是根据给定的网格尺寸和锚框的比例来构建用于目标检测的网格和锚框坐标。具体点儿就是，这个方法生成的网格用于将预测的坐标和对应的锚框进行匹配，从而定位物体在图像中的位置。
那么由于是进行CIFAR10分类任务，那么这个方法存在的必要也不是很强了。

2.其次，对于yolov5s-yaml网络结构，我们删除了中，大头的部分，仅保留小头，新的yaml文件为yolov5s-cf.yaml,在其中我们进行了对于的注释。

对于加入了DualConv方法的网络，我们命名为DualConv.yaml，在其中，我们依然删除了中、大头。
Concat 层：我们保持了 Concat 层的索引为 [-1, 6]，指向 backbone 中第6个层（即 P3/8），而去掉了其他无关的层。
Detect 层：现在的 Detect 层只依赖于 P3/8（即 13 这个层），而去掉了 P4/16 和 P5/32。

对于yolov5s-cf.yaml，我们的思路已经在其中进行了注释。

前提条件

列出所需的依赖项、环境或工具：

gitpython>=3.1.30
matplotlib>=3.3
numpy>=1.23.5
opencv-python>=4.1.1
Pillow>=9.4.0
psutil # system resources
PyYAML>=5.3.1
requests>=2.23.0
scipy>=1.4.1
thop>=0.1.1 # FLOPs computation
torch>=1.8.0 # see https://pytorch.org/get-started/locally (recommended)
torchvision>=0.9.0
tqdm>=4.64.0
ultralytics>=8.0.232

Tips:请先安装GPU版本的torch,然后,使用pip install -r requirements.txt安装对应依赖即可

一些小提示

配置部分在yolov5-master下的train.py文件中
 在此处选择合适的优化器，parser.addargument("--optimizer", type=str, choices=["SGD", "Adam", "AdamW"], default="Adam", help="optimizer")
在此处配置对应超参数，parser.addargument("--hyp", type=str, default=ROOT / "data/hyps/hyp.scratch-low.yaml", help="hyperparameters path")
在此处查看当前网络，parser.add_argument("--cfg", type=str, default="C:\yolov5-master\models\yolov5s.yaml", help="model.yaml path")

Owner

  • Login: wudixiaozhu123
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
preferred-citation:
  type: software
  message: If you use YOLOv5, please cite it as below.
  authors:
  - family-names: Jocher
    given-names: Glenn
    orcid: "https://orcid.org/0000-0001-5950-6979"
  title: "YOLOv5 by Ultralytics"
  version: 7.0
  doi: 10.5281/zenodo.3908559
  date-released: 2020-5-29
  license: AGPL-3.0
  url: "https://github.com/ultralytics/yolov5"

GitHub Events

Total
  • Watch event: 3
  • Delete event: 2
  • Issue comment event: 8
  • Push event: 10
  • Pull request event: 8
  • Create event: 9
Last Year
  • Watch event: 3
  • Delete event: 2
  • Issue comment event: 8
  • Push event: 10
  • Pull request event: 8
  • Create event: 9

Dependencies

.github/workflows/ci-testing.yml actions
  • actions/checkout v4 composite
  • actions/setup-python v5 composite
  • slackapi/slack-github-action v1.25.0 composite
.github/workflows/codeql-analysis.yml actions
  • actions/checkout v4 composite
  • github/codeql-action/analyze v3 composite
  • github/codeql-action/autobuild v3 composite
  • github/codeql-action/init v3 composite
.github/workflows/docker.yml actions
  • actions/checkout v4 composite
  • docker/build-push-action v5 composite
  • docker/login-action v3 composite
  • docker/setup-buildx-action v3 composite
  • docker/setup-qemu-action v3 composite
.github/workflows/format.yml actions
  • ultralytics/actions main composite
.github/workflows/greetings.yml actions
  • actions/first-interaction v1 composite
.github/workflows/links.yml actions
  • actions/checkout v4 composite
  • nick-invision/retry v2 composite
.github/workflows/stale.yml actions
  • actions/stale v9 composite
utils/docker/Dockerfile docker
  • pytorch/pytorch 2.0.0-cuda11.7-cudnn8-runtime build
utils/google_app_engine/Dockerfile docker
  • gcr.io/google-appengine/python latest build
pyproject.toml pypi
  • matplotlib >=3.3.0
  • numpy >=1.22.2
  • opencv-python >=4.6.0
  • pandas >=1.1.4
  • pillow >=7.1.2
  • psutil *
  • py-cpuinfo *
  • pyyaml >=5.3.1
  • requests >=2.23.0
  • scipy >=1.4.1
  • seaborn >=0.11.0
  • thop >=0.1.1
  • torch >=1.8.0
  • torchvision >=0.9.0
  • tqdm >=4.64.0
  • ultralytics >=8.0.232
requirements.txt pypi
  • Pillow >=9.4.0
  • PyYAML >=5.3.1
  • gitpython >=3.1.30
  • matplotlib >=3.3
  • numpy >=1.23.5
  • opencv-python >=4.1.1
  • pandas >=1.1.4
  • psutil *
  • requests >=2.23.0
  • scipy >=1.4.1
  • seaborn >=0.11.0
  • setuptools >=65.5.1
  • thop >=0.1.1
  • torchvision >=0.9.0
  • tqdm >=4.64.0
  • ultralytics >=8.0.232
utils/google_app_engine/additional_requirements.txt pypi
  • Flask ==2.3.2
  • gunicorn ==19.10.0
  • pip ==23.3
  • werkzeug >=3.0.1