tfep.potentials.tblite.TBLitePotential

class tfep.potentials.tblite.TBLitePotential(method: str, numbers: ndarray, positions_unit: Unit | None = None, energy_unit: Unit | None = None, precompute_gradient: bool = False, parallelization_strategy: ParallelizationStrategy | None = None, verbosity: int = 0, return_nan_on_failure: bool = False)

Bases: PotentialBase

Potential energy and gradients with tblite.

This Module wraps :class:.TBLitePotentialEnergyFunc to provide a differentiable potential energy function for training.

Warning

Currently double-backpropagation is not supported, which means force matching cannot be performed during training.

__init__(method: str, numbers: ndarray, positions_unit: Unit | None = None, energy_unit: Unit | None = None, precompute_gradient: bool = False, parallelization_strategy: ParallelizationStrategy | None = None, verbosity: int = 0, return_nan_on_failure: bool = False)

Constructor.

Parameters:

• method (str) – The method. Example 'GFN2-xTB'.

• numbers (numpy.ndarray) – Atomic numbers. Examples [8, 1, 1] for water.

• positions_unit (pint.Unit, optional) – The unit of the positions passed to the class methods. Since input Tensor``s do not have units attached, this is used to appropriately convert ``batch_positions to tblite units. If None, no conversion is performed, which assumes that the input positions are in the same units used by tblite (e.g., bohr).

• energy_unit (pint.Unit, optional) – The unit used for the returned energies (and as a consequence gradients). Since Tensor``s do not have units attached, this is used to appropriately convert tblite energies into the desired units. If ``None is performed, which means that energies and gradients will be returned in tblite units (e.g., eV).

• precompute_gradient (bool, optional) – If True, the gradient is computed in the forward pass and saved to be consumed during the backward pass. This speeds up the training, but should be deactivated if gradients are not needed. Setting this to False (default) will cause an exception if a backward pass is attempted.

• parallelization_strategy (tfep.utils.parallel.ParallelizationStrategy, optional) – The parallelization strategy used to distribute batches of energy and gradient calculations. By default, these are executed serially.

• verbosity (Literal[0, 1, 2], optional) – Verbosity to pass to the tblite Calculator (0 turns off printing, 2 is maximum verbosity).

• return_nan_on_failure (bool, optional) – If True and the single-point calculation fails (e.g., because the the SCF does not converge), the returned energy (gradient) is set to NaN (zero).

See also

TBLitePotentialEnergyFunc

More details on input parameters and implementation details.

Methods

__init__(method, numbers[, positions_unit, ...])	Constructor.
add_module(name, module)	Add a child module to the current module.
apply(fn)	Apply fn recursively to every submodule (as returned by .children()) as well as self.
bfloat16()	Casts all floating point parameters and buffers to bfloat16 datatype.
buffers([recurse])	Return an iterator over module buffers.
children()	Return an iterator over immediate children modules.
compile(*args, **kwargs)	Compile this Module's forward using torch.compile().
cpu()	Move all model parameters and buffers to the CPU.
cuda([device])	Move all model parameters and buffers to the GPU.
default_energy_unit(unit_registry)	Return the default energy units.
default_positions_unit(unit_registry)	Return the default positions units.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Set the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(batch_positions)	Compute a differential potential energy for a batch of configurations.
get_buffer(target)	Return the buffer given by target if it exists, otherwise throw an error.
get_extra_state()	Return any extra state to include in the module's state_dict.
get_parameter(target)	Return the parameter given by target if it exists, otherwise throw an error.
get_submodule(target)	Return the submodule given by target if it exists, otherwise throw an error.
half()	Casts all floating point parameters and buffers to half datatype.
ipu([device])	Move all model parameters and buffers to the IPU.
load_state_dict(state_dict[, strict, assign])	Copy parameters and buffers from state_dict into this module and its descendants.
modules()	Return an iterator over all modules in the network.
mtia([device])	Move all model parameters and buffers to the MTIA.
named_buffers([prefix, recurse, ...])	Return an iterator over module buffers, yielding both the name of the buffer as well as the buffer itself.
named_children()	Return an iterator over immediate children modules, yielding both the name of the module as well as the module itself.
named_modules([memo, prefix, remove_duplicate])	Return an iterator over all modules in the network, yielding both the name of the module as well as the module itself.
named_parameters([prefix, recurse, ...])	Return an iterator over module parameters, yielding both the name of the parameter as well as the parameter itself.
parameters([recurse])	Return an iterator over module parameters.
register_backward_hook(hook)	Register a backward hook on the module.
register_buffer(name, tensor[, persistent])	Add a buffer to the module.
register_forward_hook(hook, *[, prepend, ...])	Register a forward hook on the module.
register_forward_pre_hook(hook, *[, ...])	Register a forward pre-hook on the module.
register_full_backward_hook(hook[, prepend])	Register a backward hook on the module.
register_full_backward_pre_hook(hook[, prepend])	Register a backward pre-hook on the module.
register_load_state_dict_post_hook(hook)	Register a post-hook to be run after module's load_state_dict() is called.
register_load_state_dict_pre_hook(hook)	Register a pre-hook to be run before module's load_state_dict() is called.
register_module(name, module)	Alias for add_module().
register_parameter(name, param)	Add a parameter to the module.
register_state_dict_post_hook(hook)	Register a post-hook for the state_dict() method.
register_state_dict_pre_hook(hook)	Register a pre-hook for the state_dict() method.
requires_grad_([requires_grad])	Change if autograd should record operations on parameters in this module.
set_extra_state(state)	Set extra state contained in the loaded state_dict.
set_submodule(target, module)	Set the submodule given by target if it exists, otherwise throw an error.
share_memory()	See torch.Tensor.share_memory_().
state_dict(*args[, destination, prefix, ...])	Return a dictionary containing references to the whole state of the module.
to(*args, **kwargs)	Move and/or cast the parameters and buffers.
to_empty(*, device[, recurse])	Move the parameters and buffers to the specified device without copying storage.
train([mode])	Set the module in training mode.
type(dst_type)	Casts all parameters and buffers to dst_type.
xpu([device])	Move all model parameters and buffers to the XPU.
zero_grad([set_to_none])	Reset gradients of all model parameters.

Attributes

DEFAULT_ENERGY_UNIT	The default energy unit.
DEFAULT_POSITIONS_UNIT	The default positions unit.
T_destination
call_super_init
dump_patches
energy_unit	The energy units of the returned potential.
positions_unit	The positions unit requested for the input.
method	The method for tblite.
numbers	The atomic numbers.
precompute_gradient	Whether to compute the gradients in the forward pass to speed up the backward pass.
parallelization_strategy	The strategy used to parallelize the single-point calculations.
training

DEFAULT_ENERGY_UNIT: str = 'hartree'

The default energy unit.

DEFAULT_POSITIONS_UNIT: str = 'bohr'

The default positions unit.

classmethod default_energy_unit(unit_registry) → Quantity

Return the default energy units.

classmethod default_positions_unit(unit_registry) → Quantity

Return the default positions units.

property energy_unit: Quantity

The energy units of the returned potential.

forward(batch_positions: Tensor) → Tensor

Compute a differential potential energy for a batch of configurations.

Parameters:

batch_positions (torch.Tensor) – Shape (batch_size, 3*n_atoms). The atoms positions in units of self.positions_unit.

Returns:

potential_energy – potential_energy[i] is the potential energy of configuration batch_positions[i] in units of self.energy_unit.

Return type:

torch.Tensor

method

The method for tblite.

numbers

The atomic numbers.

parallelization_strategy

The strategy used to parallelize the single-point calculations.

property positions_unit: Quantity

The positions unit requested for the input.

precompute_gradient

Whether to compute the gradients in the forward pass to speed up the backward pass.