Mantaflow is an open-source framework targeted at fluid simulation research in Computer Graphics. Its parallelized C++ solver core, python scene definition interface and plugin system allow for quickly prototyping and testing new algorithms.
In addition, it provides a toolbox of examples for deep learning experiments with fluids. E.g., it contains examples how to build convolutional neural network setups in conjunction with tensorflow.
For deep learning with fully differentiable fluid simulations, please check out our phiflow framework.
More information on how to install, run and code with Mantaflow, please head over to our home page at http://mantaflow.com