excited module

Full Documentation for hippynn.layers.excited module. Click here for a summary page.

class LocalEnergy(feature_sizes, first_is_interacting=False)

Bases: Module

forward(all_features, mol_index, atom_index, n_molecules, n_atoms_max)

Parameters:

• all_features – list of feature tensors

• mol_index – which molecule is the atom

• atom_index – which atom in the molecule is that atom

• n_molecules – total number of molecules in the batch

• n_atoms_max – maximum number of atoms in the batch

Returns:

contributed_energy, atom_energy, atom_preenergy, prob, propensity

class NACR

Bases: Module

Compute NAC vector * ΔE. Originally in hippynn.layers.physics.

forward(charges1: Tensor, charges2: Tensor, positions: Tensor, energy1: Tensor, energy2: Tensor)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

class NACRMultiState(n_target=1)

Bases: Module

Compute NAC vector * ΔE for all paris of states. Originally in hippynn.layers.physics.

forward(charges: Tensor, positions: Tensor, energies: Tensor)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.