hippynn

This is summary documentation for hippynn module. Click here for full documentation.

API Summary for sub-modules:

• custom_kernels
• databases
• experiment
• graphs
• interfaces
• layers
• molecular_dynamics
• networks
• optimizer
• plotting
• pretraining
• tools

Links to Full Documentation:

The hippynn python package.

settings

Values for the current hippynn settings. See Library Settings for a description.

Modules

custom_kernels	Custom Kernels for hip-nn interaction sum.
databases	Organized datasets for training and prediction.
experiment	Functions for training.
graphs	Graph objects in hipppynn.
interfaces	hippynn currently has interfaces to the following other codes:
layers	Pytorch modules that represent composable pieces of models.
molecular_dynamics	Molecular dynamics driver with great flexibility and customizability regarding which quantities which are evolved and what algorithms are used to evolve them.
networks	Composite pytorch modules that represent larger models.
optimizer	Functionality for Batch geometry optimization of configurations under a potential energy surface..
plotting	Facilities for plotting data during validation/test evaluations.
pretraining	Things to do before training, i.e. initialization of network and diagnostics.
tools	Misc.