fine-tuned-yolo

This repository is forked from yolov5. The original model is here fine-tuned on a drone detection dataset from kaggle.com

https://github.com/frabranca/fine-tuned-yolo

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 (7.5%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

This repository is forked from yolov5. The original model is here fine-tuned on a drone detection dataset from kaggle.com

Basic Info
  • Host: GitHub
  • Owner: frabranca
  • License: agpl-3.0
  • Language: Python
  • Default Branch: main
  • Size: 15.1 MB
Statistics
  • Stars: 1
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed over 1 year ago
Metadata Files
Readme Contributing License Citation

README.md

Fine-Tuned YOLOV5 for Drone Detection

YOLOv5 🚀 is the world's most loved vision AI, representing Ultralytics open-source research into future vision AI methods, incorporating lessons learned and best practices evolved over thousands of hours of research and development.

Project Contribution

The chosen dataset to fine-tune the model is found on kaggle. This dataset includes various images of aerial vehicles flying. The original YOLOV5 was trained on 80 different classes of objects, hence its performance on the kaggle dataset is poor. This project focuses on specializing the original model by fine-tuning it on the kaggle dataset and including only 3 possible object classes (airplanes, drones, helicopters).

Side Image 1 Main Image Side Image 2

Training

The model was trained with the following settings:

  • batch size: 16;
  • epochs: 50;
  • train dataset: 10799 images;
  • test dataset: 596 images;

Owner

  • Name: Francesco Branca
  • Login: frabranca
  • 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: 1
  • Delete event: 1
  • Issue comment event: 5
  • Push event: 13
  • Pull request event: 2
  • Create event: 4
Last Year
  • Watch event: 1
  • Delete event: 1
  • Issue comment event: 5
  • Push event: 13
  • Pull request event: 2
  • Create event: 4