Skip to content
No description, website, or topics provided.
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
Experiments
data
deepsphere
figures
report
results
.gitignore
LICENCE.txt
README.md
demo.ipynb
hyperparameters.py
postBuild
requirements.txt

README.md

An empirical study of spherical convolutional neural networks

Frédérick Gusset, Nathanaël Perraudin, Michaël Defferrard

The code in this repository is based on DeepSphere and regroups all experiments performed in the master thesis "An empirical study of spherical convolutional neural networks". This master project was performed in the LTS2 lab at EPFL, during Spring semester 2019.

Installation

For a local installation, follow the below instructions.

  1. Clone this repository.

    git clone https://github.com/Droxef/PDMdeepsphere.git
    cd PDMdeepSphere
  2. Install the dependencies.

    pip install -r requirements.txt

    Note: if you will be working with a GPU, comment the tensorflow==1.6.0 line in requirements.txt and uncomment the tensorflow-gpu==1.6.0 line.

    Note: the code has been developed and tested with Python 3.5.

  3. Play with the Jupyter notebooks.

    jupyter notebook

Experiments

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.

  1. SHREC17

  2. ModelNet40

    • demo MN40 experiment
    • analyze rotation Analyze the behaviour when adding different rotation perturbations
  3. GHCN

    • test Analyze of the dataset
    • demo GHCN diffent taks
  4. Climate

  5. Graphs

  6. Irregular pooling

License & co

The content of this repository is released under the terms of the MIT license.

You can’t perform that action at this time.