pyiqa
=====

.. py:module:: pyiqa


Submodules
----------

.. toctree::
   :maxdepth: 1

   /autoapi/pyiqa/api_helpers/index
   /autoapi/pyiqa/archs/index
   /autoapi/pyiqa/data/index
   /autoapi/pyiqa/default_model_configs/index
   /autoapi/pyiqa/losses/index
   /autoapi/pyiqa/matlab_utils/index
   /autoapi/pyiqa/metrics/index
   /autoapi/pyiqa/models/index
   /autoapi/pyiqa/pyiqa_cmd/index
   /autoapi/pyiqa/test/index
   /autoapi/pyiqa/train/index
   /autoapi/pyiqa/train_nsplits/index
   /autoapi/pyiqa/utils/index




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

.. py:function:: create_metric(metric_name, as_loss=False, device=None, **kwargs)

.. py:function:: list_models(metric_mode=None, filter='', exclude_filters='')

   Return list of available model names, sorted alphabetically
   :param filter:
   :type filter: str
   :param exclude_filters:
   :type exclude_filters: str or list[str]

   .. rubric:: Example

   model_list('*ssim*') -- returns all models including 'ssim'


.. py:function:: get_dataset_info(dataset_name=None)

.. py:function:: load_dataset(name: str, data_root: str = './datasets', force_download: bool = False, dataset_opts: Optional[Dict[str, Any]] = None, **kwargs: Any) -> Any

   Load a dataset from specified location, downloading if necessary.

   :param name: Name of the dataset to load
   :type name: str
   :param data_root: Root directory for dataset storage
   :type data_root: str
   :param force_download: Whether to force download even if files exist
   :type force_download: bool
   :param dataset_opts: Additional dataset options
   :type dataset_opts: Optional[Dict[str, Any]]
   :param \*\*kwargs: Additional arguments passed to dataset configuration
   :type \*\*kwargs: Any

   :returns: Dataset object
   :rtype: Any