Research-oriented differentiable fluid simulation framework
ΦFlow is an open-source simulation toolkit built for optimization and machine learning applications. It is written mostly in Python and can be used with NumPy, TensorFlow or PyTorch. The close integration with machine learning frameworks allows it to leverage their automatic differentiation functionality, making it easy to build end-to-end differentiable functions involving both learning models and physics simulations.
This is major version 2 of ΦFlow. Version 1 is available in the branchrelease history.
Installation with pip on Python 3.6 or newer:
bash $ pip install phiflowInstall TensorFlow or PyTorch in addition to ΦFlow to enable machine learning capabilities and GPU execution. See the detailed installation instructions on how to compile the custom CUDA operators and verify your installation.
An overview of all available documentation can be found here.
If you would like to get right into it and have a look at some code, check out the tutorial notebook on Google Colab. It lets you run fluid simulations with ΦFlow in the browser. Also check out the explanation of common fluid simulation operations.
The following introductory demos are also helpful to get started with writing your own scripts using ΦFlow:
The Version history lists all major changes since release.
The releases are also listed on PyPI.
Contributions are welcome! Check out this document for guidelines.
This work is supported by the ERC Starting Grant realFlow (StG-2015-637014) and the Intel Intelligent Systems Lab.