Data

Tools

Indexes

Applications

Experiments

Open Source Science

yolov8_prune

This project demonstrates a systematic approach to model optimization, showcasing the importance of fine-tuning in the context of model pruning. It provides a foundation for further research and development in the field of efficient deep learning model deployment.

https://github.com/garlic-byte/yolov8_prune

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 (3.0%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

This project demonstrates a systematic approach to model optimization, showcasing the importance of fine-tuning in the context of model pruning. It provides a foundation for further research and development in the field of efficient deep learning model deployment.

Basic Info
  • Host: GitHub
  • Owner: garlic-byte
  • Language: Python
  • Default Branch: master
  • Size: 997 KB
Statistics
  • Stars: 14
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme Citation

README.md

yolov8模型剪枝项目

项目简介

本项目通过应用模型剪枝技术，旨在降低深度学习模型的复杂性和计算负载，并通过回调训练进一步提升模型的效率和性能。

功能特点

  • 模型剪枝：去除冗余权重，精简模型结构。
  • 回调训练：剪枝后对模型进行再训练，优化性能。
  • 性能优化：在减小模型体积的同时，保持或提高模型的准确性和泛化能力。

使用技术

  • 深度学习框架：PyTorch
  • 配置和权重文件：用于模型定义和初始化。
  • Python脚本：自定义脚本进行模型训练和调整。

运行环境

  • Python 3.8
  • 深度学习库：PyTorch
  • CUDA环境（推荐，用于GPU加速）

安装指南

  1. 克隆项目仓库到本地机器 ```bash git clone https://github.com/jasonDasuantou/yolov8prune.git python trainstep1.py

Owner

  • Login: garlic-byte
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
preferred-citation:
  type: software
  message: If you use this software, please cite it as below.
  authors:
  - family-names: Jocher
    given-names: Glenn
    orcid: "https://orcid.org/0000-0001-5950-6979"
  - family-names: Chaurasia
    given-names: Ayush
    orcid: "https://orcid.org/0000-0002-7603-6750"
  - family-names: Qiu
    given-names: Jing
    orcid: "https://orcid.org/0000-0003-3783-7069"
  title: "YOLO by Ultralytics"
  version: 8.0.0
  # doi: 10.5281/zenodo.3908559  # TODO
  date-released: 2023-1-10
  license: AGPL-3.0
  url: "https://github.com/ultralytics/ultralytics"

GitHub Events

Total
Last Year