dgs.models.embedding_generator.embedding_generator.EmbeddingGeneratorModule

class dgs.models.embedding_generator.embedding_generator.EmbeddingGeneratorModule(*args: Any, **kwargs: Any)

Base class for handling modules of embedding generators.

Description

Given some model-specific data through the State, child models of this class will predict one embedding per single sample (detection) of data, describing it. The child models should also work for batched input data.

Params:

• embedding_size (int) – The size of the embedding. This size does not necessarily have to match other embedding sizes.

• nof_classes (int) – The number of classes in the dataset. Used during training to predict the id.

Optional Params:

• embedding_key (str, optional) – The key to use to retrieve the embedding of the image. Default DEF_VAL.embed_gen.embedding_key.

• save_embeddings (bool, optional) – Whether to save the computed embeddings in the given State. Default DEF_VAL.embed_gen.save_embeddings.

Methods

__init__(config: dict[str, any], path: list[str])

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.

embedding_key_exists(s: State) → bool

Return whether the embedding_key of this model exists in a given state.

abstract forward(ds: State) → torch.Tensor

Predict next outputs, given any data in a State object, using this Re-ID model.

Returns:

The generated embeddings as tensor of shape [N x embedding_size].

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.
embedding_size	The size of the embedding.
nof_classes	The number of classes in the dataset / embedding.