Data

Tools

Indexes

Applications

Experiments

Open Source Science

tree_is_all_you_need

Predicting tree deformation using GNN

https://github.com/chjohnkim/tree_is_all_you_need

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 (11.6%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

Predicting tree deformation using GNN

Basic Info
  • Host: GitHub
  • Owner: chjohnkim
  • License: mit
  • Language: Python
  • Default Branch: main
  • Size: 15.4 MB
Statistics
  • Stars: 3
  • Watchers: 4
  • Forks: 4
  • Open Issues: 1
  • Releases: 0
Created almost 4 years ago · Last pushed over 3 years ago
Metadata Files
Readme License Citation

README.md

"Tree is All You Need" : Predicting tree deformation using GNN

Mark Lee, Joe Huang, John Kim

We provide PyTorch code for our 11-785 Introduction to Deep Learning course project.

Our goal for this project is to learn the complex physics model of trees. More specifically, we want to predict the deformation of trees when an external force is applied. Obtaining a more accurate model of tree is important for the robot, as it can lead to safer and more robust manipulation in agriculture. For this purpose, we use recent advancements in Graph Neural Networks and take advantage of graph-like tree structures to learn and predict the dynamics of tree deformation. We share our custom collected synthetic dataset as well as our codebase.

Paper: Coming Soon
Video: Click Here

Prerequisites

This code is developed with Python3 (python3).
It is recommended use Anaconda to set up the environment. Install the dependencies and activate the environment tree-env with bash conda env create --file requirements.yaml python=3 conda activate tree-env

Dataset

  • #### Synthetic data We collected a tree deformation dataset simulated in Isaac Gym, which can be found in the Google Drive. For convenience, you can download them with the following script: (under this repo) bash gdown --id 1YwUABOUg7ukxlmDqN1GojCtuJsZQ57J5 # download tree_dataset.zip unzip tree_dataset.zip rm -f tree_dataset.zip mv tree_dataset data/tree_dataset The data directory should contain the subdirectory tree_dataset.

Running the code

  • #### Training: bash python main_train.py
  • #### Testing: bash python main_test.py
  • #### Generating GIF animations: bash python main_gif.py All the results will be stored in the directory output/.

Code contributed and maintained by:

Owner

  • Name: John
  • Login: chjohnkim
  • Kind: user
  • Location: Pittsburgh, PA
  • Company: Carnegie Mellon University

PhD student, CMU Robotics Institute

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Huang"
  given-names: "Hung-Jui"
  orcid: "https://orcid.org/0000-0003-0184-5155"
- family-names: "Kim"
  given-names: "Chung Hee"
  orcid: "https://orcid.org/0000-0001-7710-5984"
- family-names: "Lee"
  given-names: "Moonyoung"
  orcid: "https://orcid.org/0000-0003-3275-5304"
title: "tree_is_all_you_need"
version: 1.0.0
date-released: 2022-07-24
url: "https://github.com/chjohnkim/tree_is_all_you_need"

GitHub Events

Total
  • Watch event: 1
Last Year
  • Watch event: 1