czbenchmarks.models.implementations
===================================

.. py:module:: czbenchmarks.models.implementations


Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/czbenchmarks/models/implementations/base_model_implementation/index


Classes
-------

.. autoapisummary::

   czbenchmarks.models.implementations.BaseModelImplementation


Package Contents
----------------

.. py:class:: BaseModelImplementation(**user_kwargs)

   Bases: :py:obj:`czbenchmarks.models.validators.base_model_validator.BaseModelValidator`, :py:obj:`abc.ABC`


   Abstract base class for model implementations.

   Handles common model operations like:
   - Loading datasets
   - Downloading model weights
   - Running inference
   - Saving results


   .. py:attribute:: datasets
      :type:  List[czbenchmarks.datasets.BaseDataset]

      List of datasets to process


   .. py:attribute:: model_weights_dir
      :type:  str

      Directory containing model weights


   .. py:attribute:: args
      :type:  argparse.Namespace

      Parsed command-line arguments


   .. py:method:: get_model_weights_subdir(dataset: czbenchmarks.datasets.BaseDataset) -> str
      :abstractmethod:


      Get subdirectory for model variant weights.

      :param dataset: Dataset being processed

      :returns: Subdirectory path or empty string if not needed



   .. py:method:: download_model_weights(dataset: czbenchmarks.datasets.BaseDataset) -> None

      Download and verify model weights.

      :param dataset: Dataset being processed



   .. py:method:: run_model(dataset: czbenchmarks.datasets.BaseDataset) -> None
      :abstractmethod:


      Implement model-specific inference logic



   .. py:method:: parse_args() -> argparse.Namespace

      Centralized argument parsing using subclass-defined parser



   .. py:method:: create_parser() -> argparse.ArgumentParser | None

      Subclasses implement to define their CLI arguments



   .. py:method:: run(datasets: Optional[czbenchmarks.datasets.BaseDataset | List[czbenchmarks.datasets.BaseDataset]] = None)

      Run the full model pipeline.

      1. Load and validate all datasets
      2. Download model weights
      3. Run inference
      4. Save results

      :param datasets: List of datasets to process

      :raises FileNotFoundError: If no input datasets found