The official implementation of the "Steerable 3D Spherical Neurons" paper, Proceedings of the 39th International Conference on Machine Learning, ICML 2022, 17-23 July, 2022
(best viewed as an image in a new tab)
📋We achieved the original results with Python 3.7.10,
torch==1.8.1
,scipy==1.6.1
,numpy==1.20.3
. Other dependencies includematplotlib
andtqdm
.
To install the requirements, run:
pip install -r requirements.txt
The utkinect_skeletons_data
folder contains the 3D skeleton data that we extracted and preprocessed from UTKinect-Action3D dataset. The preprocessing and data split are described in Section 5.1 in the paper.
The demo_[dataset_name].ipynb
notebooks demonstrate a step-by-step construction of the proposed steerable spherical model, as well as the experiments with the corresponding datasets reported in the paper.
@InProceedings{pmlr-v162-melnyk22a,
title = {Steerable 3{D} Spherical Neurons},
author = {Melnyk, Pavlo and Felsberg, Michael and Wadenb{\"a}ck, M{\aa}rten},
booktitle = {Proceedings of the 39th International Conference on Machine Learning},
pages = {15330--15339},
year = {2022},
editor = {Chaudhuri, Kamalika and Jegelka, Stefanie and Song, Le and Szepesvari, Csaba and Niu, Gang and Sabato, Sivan},
volume = {162},
series = {Proceedings of Machine Learning Research},
month = {17--23 Jul},
publisher = {PMLR},
pdf = {https://proceedings.mlr.press/v162/melnyk22a/melnyk22a.pdf},
url = {https://proceedings.mlr.press/v162/melnyk22a.html}
}