dgs.models.combine.static.StaticAlphaCombine¶
- class dgs.models.combine.static.StaticAlphaCombine(*args: Any, **kwargs: Any)[source]¶
Weight two or more similarity matrices using constant (float) values for alpha.
- Params:
alpha (list[float]) – A list containing the constant weights for the different similarities. The weights should be probabilities and therefore sum to one and lie within [0..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, **_kwargs) torch.Tensor [source]¶
Given alpha from the configuration file and args of the same length, multiply each alpha with each matrix and compute the sum.
- Parameters:
tensors (tuple[torch.Tensor, ...]) – A number of similarity tensors. Should have the same length as alpha. All the tensors should have the same size.
- Returns:
The weighted similarity matrix as FloatTensor.
- Raises:
ValueError – If the
tensors
argument has the wrong shapeTypeError – If the
tensors
argument contains an object that is not a torch.tensor.
- terminate() None [source]¶
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
Get the device of this module.
Get whether this module is set to training-mode.
Get the name of the module.
Get the name of the module.
Get the escaped name of the module usable in filepaths by replacing spaces and underscores.
Get the (floating point) precision used in multiple parts of this module.