title	emoji	colorFrom	colorTo	sdk	app_file	pinned
YOLOv8-TO Demo	🏗️	yellow	green	gradio	app.py	false

YOLOv8-TO

Code for the paper:

"From Density to Geometry: YOLOv8 Instance Segmentation for Reverse Engineering of Optimized Structures"

• Read the paper: arXiv.
• Try it out here: Demo

Table of Contents

• Overview
• Reference
• Installation
  • Prerequisites
  • Installing
• Datasets
• Training
• Inference

Overview

Brief description of what the project does and the problem it solves. Include a link or reference to the original article that inspired or is associated with this implementation.

Demo

The nano version of the model is hosted on Hugging Face Spaces:

• Try the YOLOv8-TO Nano model with your own images!

Reference

This code aims to reproduce the results presented in the research article:

@misc{rochefortbeaudoin2024density,
      title={From Density to Geometry: YOLOv8 Instance Segmentation for Reverse Engineering of Optimized Structures}, 
      author={Thomas Rochefort-Beaudoin and Aurelian Vadean and Sofiane Achiche and Niels Aage},
      year={2024},
      eprint={2404.18763},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

Installation

Prerequisites

This package comes with a fork of the ultralytics package in the yolov8-to directory. The fork is necessary to add the functionality of the design variables regression.

Installing

git clone https://github.com/COSIM-Lab/YOLOv8-TO.git
cd YOLOv8-TO/yolov8-to
pip install -e .

Datasets

Links to the dataset on HuggingFace:

• YOLOv8-TO_Data

The Huggingface dataset contains the following datasets (see paper for details):

• MMC
• MMC-random
• SIMP
• SIMP_5%
• OOD

If you want to use one of the linked datasets, please unzip it inside of the datasets folder. Training labels are provided for the MMC and MMC-random data. To train on the data, please update the data.yaml file with the correct path to the dataset.

path:  # dataset root dir

Training

To train the model, make sure the train dataset is setup according to the above section and according to the documentation from ultralytics: https://docs.ultralytics.com/datasets/

Refer to the notebook YOLOv8_TO.ipynb for an example of how to train the model.

Inference

Refer to the notebook YOLOv8_TO.ipynb for an example of how to perform inference with the trained model.