torch_concepts.nn.BaseConstructor

class BaseConstructor(input_size: int, annotations: Annotations, encoder: LazyConstructor | Module, predictor: LazyConstructor | Module, *args, **kwargs)

Abstract base class for all concept-based models.

This class provides the foundation for building concept-based neural networks.

input_size

Size of the input features.

Type:

int

annotations

Concept annotations with metadata.

Type:

Annotations

labels

List of concept labels.

Type:

List[str]

name2id

Mapping from concept names to indices.

Type:

Dict[str, int]

Parameters:

• input_size – Size of the input features.

• annotations – Annotations object containing concept metadata.

• encoder – LazyConstructor layer for encoding root concepts from inputs.

• predictor – LazyConstructor layer for making predictions from concepts.

• *args – Variable length argument list.

• **kwargs – Arbitrary keyword arguments.

Example

>>> import torch
>>> from torch_concepts import Annotations, AxisAnnotation
>>> from torch_concepts.nn import LazyConstructor
>>> from torch_concepts.nn.modules.mid.base.model import BaseConstructor
>>> from torch.distributions import RelaxedBernoulli
>>>
>>> # Create annotations for concepts
>>> concept_labels = ('color', 'shape', 'size')
>>> cardinalities = [1, 1, 1]
>>> metadata = {
...     'color': {'distribution': RelaxedBernoulli},
...     'shape': {'distribution': RelaxedBernoulli},
...     'size': {'distribution': RelaxedBernoulli}
... }
>>> annotations = Annotations({1: AxisAnnotation(
...     labels=concept_labels,
...     cardinalities=cardinalities,
...     metadata=metadata
... )})
>>>
>>> # Create a concrete model class
>>> class MyConceptModel(BaseConstructor):
...     def __init__(self, input_size, annotations, encoder, predictor):
...         super().__init__(input_size, annotations, encoder, predictor)
...         # Build encoder and predictor
...         self.encoder = self._encoder_builder
...         self.predictor = self._predictor_builder
...
...     def forward(self, x):
...         concepts = self.encoder(x)
...         predictions = self.predictor(concepts)
...         return predictions
>>>
>>> # Create encoder and predictor propagators
>>> encoder = torch.nn.Linear(784, 3)  # Simple encoder
>>> predictor = torch.nn.Linear(3, 10)  # Simple predictor
>>>
>>> # Instantiate model
>>> model = MyConceptModel(
...     input_size=784,
...     annotations=annotations,
...     encoder=encoder,
...     predictor=predictor
... )
>>>
>>> # Generate random input (e.g., flattened MNIST image)
>>> x = torch.randn(8, 784)  # batch_size=8, pixels=784
>>>
>>> # Forward pass
>>> output = model(x)
>>> print(output.shape)  # torch.Size([8, 10])
>>>
>>> # Access concept labels
>>> print(model.labels)  # ('color', 'shape', 'size')
>>>
>>> # Get concept index by name
>>> idx = model.name2id['color']
>>> print(idx)  # 0

__init__(input_size: int, annotations: Annotations, encoder: LazyConstructor | Module, predictor: LazyConstructor | Module, *args, **kwargs)

Initialize internal Module state, shared by both nn.Module and ScriptModule.

Methods

__init__(input_size, annotations, encoder, ...)	Initialize internal Module state, shared by both nn.Module and ScriptModule.
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.
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(*input)	Define the computation performed at every call.
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[, 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