This plugin enables the use of TensorFlow in a HOOMD-blue simulation to compute quantities like forces and collective variables and do learning while running a simulation. You may also use it without hoomd-blue to process trajectories via MDAnalysis. Please see here for documentation for install and usage instructions.
HOOMD-TF can be used for a variety of tasks such as online force-matching, online machine learning in HOOMD-blue simulations, and arbitrary collective variable calculations using TensorFlow tensor operations. Because both HOOMD-blue and TensorFlow are GPU-accelerated, HOOMD-TF was designed with speed in mind, and minimizes latency with a GPU-GPU communication scheme. Of particular interest, HOOMD-TF allows for online machine learning with early termination, rather than the more tradditional batch learning approach for MD+ML.
HOOMD-TF includes several utility functions as convenient built-ins, such as:
- RDF calculation
- EDS Biasing (See this paper)
- Coarse-Grained simulation force matching
In addition to all these, the TensorFlow interface of HOOMD-TF makes implementing arbitrary ML models as easy as it is in TensorFlow, by exposing the HOOMD-blue neighbor list and particle positions to TensorFlow. This enables GPU-accelerated tensor calculations, meaning arbitrary collective variables can be treated in the TensorFlow model framework, as long as they can be expressed as tensor operations on particle positions or neighbor lists.
See example notebooks here to learn about what HOOMD-TF can do.
The following packages are required to compile:
tensorflow >= 2.3
hoomd >= 2.6
tbb-devel (only for hoomd if installed with conda)
tbb-devel is required when using the
HOOMD-blue conda release. It is not automatically installed when
installing HOOMD-blue, so use conda install -c conda-forge tbb-devel
to install. The TensorFlow version should be TensorFlow 2.3 release.
It is recommended you install via pip.
Please use the following citation:
HOOMD-TF: GPU-Accelerated, Online Machine Learning in the HOOMD-blue Molecular Dynamics Engine. R Barrett, M Chakraborty, DB Amirkulova, HA Gandhi, G Wellawatte, and AD White (2020) Journal of Open Source Software doi: 10.21105/joss.02367
© HOOMD-TF Developers