mlcolvar.core.transform.descriptors.MultipleDescriptors

class mlcolvar.core.transform.descriptors.MultipleDescriptors(descriptors_list: list, n_atoms: int)

Bases: Module

Wrapper class to combine multiple descriptor transform objects acting on the same set of atomic positions

__init__(descriptors_list: list, n_atoms: int)

_summary_

Parameters:

• descriptors_list (list) – List of descriptor transform objects to be combined

• n_atoms (int) – Number of atoms in the system

Methods

__init__(descriptors_list, n_atoms)	_summary_
forward(pos)	Define the computation performed at every call.

property device

Check device consistency and return device

forward(pos)

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.

Attributes

T_destination
call_super_init
device	Check device consistency and return device
dump_patches
training