dgs.models.combine.dynamic.AlphaCombine

class dgs.models.combine.dynamic.AlphaCombine(*args: Any, **kwargs: Any)

Compute a weighted sum of multiple given similarity matrices and given alpha weights.

More precisely, given a similarity matrix / tensor with shape [N x T], and one alpha value per similarity, compute the weighted sum of all the similarity matrices. The module will make sure, that \(\sum_N \alpha_i = 1\).

Methods

__init__(*args, **kwargs)

configure_torch_module(module: torch.nn.Module, train: bool | None = None) → torch.nn.Module

Set compute mode and send model to the device or multiple parallel devices if applicable.

Parameters:

• module – The torch module instance to configure.

• train – Whether to train or eval this module, defaults to the value set in the base config.

Returns:

The module on the specified device or in parallel.

forward(*tensors: torch.Tensor, alpha: torch.Tensor | None = None, **_kwargs) → torch.Tensor

The forward call of this module combines an arbitrary number of similarity matrices using an importance weight \(\alpha\).

Parameters:

• tensors – N similarity matrices as a tuple of tensors. All tensors should have values in range [0,1], be of the same shape [D x T], and be on the same device.

• alpha – A tensor containing weights in range [0,1]. Alpha can have one of the following shapes: [N] or [N x D]. The alpha tensor should be on the same device as the other tensors.

Returns:

The weighted similarity matrix.

Return type:

torch.Tensor

Raises:

• ValueError – If alpha or the matrices have invalid shapes.

• RuntimeError – If the tensors are not on the same device.

• TypeError – If one of the tensors or alpha is not of type class:torch.Tensor.

terminate() → None

Terminate this module and all of its submodules.

If nothing has to be done, just pass. Is used for terminating parallel execution and threads in specific models.

validate_params(validations: dict[str, list[str | type | tuple[str, any] | Callable[[any, any], bool]]], attrib_name: str = 'params') → None

Given per key validations, validate this module’s parameters.

Throws exceptions on invalid or nonexistent params.

Parameters:

• attrib_name – name of the attribute to validate, should be “params” and only for base class “config”

• validations –

  Dictionary with the name of the parameter as key and a list of validations as value. Every validation in this list has to be true for the validation to be successful.

  The value for the validation can have multiple types:

  • A lambda function or other type of callable

  • A string as reference to a predefined validation function with one argument

  • None for existence

  • A tuple with a string as reference to a predefined validation function with one additional argument

  • It is possible to write nested validations, but then every nested validation has to be a tuple, or a tuple of tuples. For convenience, there are implementations for “any”, “all”, “not”, “eq”, “neq”, and “xor”. Those can have data which is a tuple containing other tuples or validations, or a single validation.

  • Lists and other iterables can be validated using “forall” running the given validations for every item in the input. A single validation or a tuple of (nested) validations is accepted as data.

Example

This example is an excerpt of the validation for the BaseModule-configuration.

>>> validations = {
    "device": [
            str,
            ("any",
                [
                    ("in", ["cuda", "cpu"]),
                    ("instance", torch.device)
                ]
            )
        ],
        "print_prio": [("in", PRINT_PRIORITY)],
        "callable": (lambda value: value == 1),
    }

And within the class __init__() call:

>>> self.validate_params()

Raises:

• InvalidParameterException – If one of the parameters is invalid.

• ValidationException – If the validation list is invalid or contains an unknown validation.

Attributes

device	Get the device of this module.
is_training	Get whether this module is set to training-mode.
module_name	Get the name of the module.
module_type
name	Get the name of the module.
name_safe	Get the escaped name of the module usable in filepaths by replacing spaces and underscores.
precision	Get the (floating point) precision used in multiple parts of this module.
softmax