DeepPhysX

Interfacing AI with simulation

The DeepPhysX project provides Python packages allowing users to easily interface their numerical simulations with learning algorithms.

Features

DeepPhysX is a full Python3 projects with the following main features:

• Generate a dataset with synthetic data from numerical simulations;
• Train an artificial neural network with a synthetic dataset;
• Use the predictions of a trained network in a numerical simulation.

The full list of features is detailed in the documentation.

Quick install

# Option 1 (USERS): install with pip
$ pip install git+https://github.com/mimesis-inria/DeepPhysX.git

# Option 2 (DEVS): install as editable
$ git clone https://github.com/mimesis-inria/DeepPhysX.git
$ cd DeepPhysX
$ pip install -e .