Skip to content

Latest commit

 

History

12 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Introduction

This repository is meant to reproduce the content of the article E. Bretin & R. Denis & S. Masnou & G. Terii, 2022, Learning phase field mean curvature flows with neural networks.

When the article goes out in 2022, we started to make a proper repo that should reproduce all figures of the article but we failed to exactly reproduce some of them due to the fact that we lost some experiment's exact configuration (and code version) among all experiments that we have done. This repository has been put aside when we had to move on to other projects.

The current content is thus incomplete and doesn't match exactly what is visible in the original article.

Installation

This repository relies on nnpf package that requires a Python version between 3.8 and 3.10 (versions above have not been tested).

Conda

You can use a currently installed Python or, for example, create a miniconda/anaconda environment:

conda env create -f environment.yml
conda activate nnpf_jcp2022

If you need a specific computation platform context, like an older CUDA version or the support of ROCm, you should install PyTorch manually using the instructions available on the official website.

Install from Pypi

pip install nnpf==1.0.2

Computing the content of the article

This repository features already (partially) reproduced checkpoints and figures but you can compute them again if you want.

All the content

To compute all the content of the article (as far as reproduced in this repo), including the neural network checkpoints and the figure:

make clean
make

If you want to use a GPU (for model training only), you can add the argument options="--gpus=1" or even force everything (including the dataset) to be on the device with options="--force_gpu", for example :

make -j2 options="--force_gpu"

The models only

To only train the models:

make clean_models
make models

It takes about 2 hours on a (not heavily loaded) Nvidia V100s using the command-line:

make -j2 options="--force_gpu"

The figures only

To compute only the figures given already computed checkpoints:

make clean_figures
make figures

It takes about 10 minutes on a CPU Intel(R) Xeon(R) E-2176.

About

Reproducting (partially) the content of JCP2022 article

Resources

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages