torch_concepts.nn.LazyConstructor

class LazyConstructor(module_cls: type[Module], *module_args, **module_kwargs)

Delayed module instantiation wrapper for flexible neural network construction.

The LazyConstructor class stores a module class and its initialization arguments, delaying actual instantiation until the required feature dimensions are known. This enables building models where concept dimensions are determined dynamically.

module

The instantiated module (None until build() is called).

Type:

torch.nn.Module

Parameters:

• module_cls – The class of the module to instantiate.

• *module_args – Positional arguments for module instantiation.

• **module_kwargs – Keyword arguments for module instantiation.

Example

>>> import torch
>>> from torch_concepts.nn import LazyConstructor
>>> from torch_concepts.nn import LinearConceptToConcept
>>>
>>> # Create a propagator for a predictor
>>> lazy_constructor = LazyConstructor(
...     LinearConceptToConcept,
...     activation=torch.sigmoid
... )
>>>
>>> # Build the module when dimensions are known
>>> module = lazy_constructor.build(
...     out_concepts=3,
...     in_concepts=5,
...     in_embeddings=None,
... )
>>>
>>> # Use the module
>>> x = torch.randn(2, 5)
>>> output = lazy_constructor(x)
>>> print(output.shape)
torch.Size([2, 3])

__init__(module_cls: type[Module], *module_args, **module_kwargs)

Initialize the LazyConstructor with a module class and its arguments.

Parameters:

• module_cls – The class of the module to instantiate later.

• *module_args – Positional arguments for module instantiation.

• **module_kwargs – Keyword arguments for module instantiation.

Methods

__init__(module_cls, *module_args, ...)	Initialize the LazyConstructor with a module class and its arguments.
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.
build(out_concepts[, in_concepts, in_embeddings])	Build and instantiate the underlying module with required arguments.
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.
double()	Casts all floating point parameters and buffers to double datatype.
eval()	Set the module in evaluation mode.
extra_repr()	Return the extra representation of the module.
float()	Casts all floating point parameters and buffers to float datatype.
forward(x, *args, **kwargs)	Forward pass through the instantiated module.
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([remove_duplicate])	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[, strict])	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

T_destination
call_super_init
dump_patches
training