An empirical study of spherical convolutional neural networks
The code in this repository is based on DeepSphere and contains all the experiments performed for the master thesis "An empirical study of spherical convolutional neural networks". The project was performed in the LTS2 lab at EPFL during the spring semester of 2019, under the supervision of Nathanaël Perraudin and Michaël Defferrard.
For a local installation, follow the below instructions.
Clone this repository.
git clone https://github.com/Droxef/PDMdeepsphere.git cd PDMdeepSphere
Install the dependencies.
pip install -r requirements.txt
Note: if you will be working with a GPU, comment the
requirements.txtand uncomment the
Note: the code has been developed and tested with Python 3.5.
Play with the Jupyter notebooks.
The different benchmarks are regrouped in the Experiment folder, and each has at least one notebook to rerun the experiment and reproduce the results in the report.
- equiangular_and_other_graphs Construct an equiangular graph and analyze its properties
- Irregular_pooling Find ways to use pooling on random part of sphere
The content of this repository is released under the terms of the MIT license.