sequince_density.flows.base
===========================

.. py:module:: sequince_density.flows.base

.. autoapi-nested-parse::

   Shared base class for normalizing-flow adapters.



Classes
-------

.. autoapisummary::

   sequince_density.flows.base.Flow


Module Contents
---------------

.. py:class:: Flow(dims, device = None, particle_transform = None)

   Base class for backend flow adapters.

   This mirrors the Aspire flow surface closely enough for future migration,
   while remaining compatible with ``sequince.transforms.FlowTransform``.

   Periodic particle transforms, including components of composite transforms,
   are unsupported because these adapters do not sum over periodic images.


   .. py:attribute:: xp
      :type:  types.ModuleType | None
      :value: None



   .. py:attribute:: dims


   .. py:attribute:: device
      :value: None



   .. py:property:: particle_transform
      :type: sequince.transforms.ParticleTransform


      Coordinate transform used for sampling and density evaluation.


   .. py:attribute:: fit_history
      :type:  dict[str, list[float]]


   .. py:method:: fit(samples, context=None)
      :abstractmethod:



   .. py:method:: forward(samples, context=None)
      :abstractmethod:



   .. py:method:: inverse(samples, context=None)
      :abstractmethod:



   .. py:method:: log_prob(samples, context=None)
      :abstractmethod:



   .. py:method:: sample(n_samples, context=None, *, rng=None)
      :abstractmethod:



   .. py:method:: sample_and_log_prob(n_samples, context=None, *, rng=None)
      :abstractmethod:



   .. py:method:: fit_particle_transform(x, context=None, *, rng=None)


   .. py:method:: forward_particle_transform(x, context=None, *, rng=None)


   .. py:method:: inverse_particle_transform(x, context=None, *, auxiliary=None, rng=None)