skself.partial_annotations.lazy_model
=====================================

.. py:module:: skself.partial_annotations.lazy_model


Classes
-------

.. autoapisummary::

   skself.partial_annotations.lazy_model.LazyLossWrapper
   skself.partial_annotations.lazy_model.LazyMetricWrapper
   skself.partial_annotations.lazy_model.LazySegmentationModel


Functions
---------

.. autoapisummary::

   skself.partial_annotations.lazy_model.pop_channel


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

.. py:class:: LazyLossWrapper(base_loss, mask_index=-1)

   Bases: :py:obj:`tensorflow.keras.losses.Loss`


   .. py:method:: call(y_true, y_pred)


   .. py:attribute:: base_loss


   .. py:attribute:: mask_index
      :value: -1



.. py:class:: LazyMetricWrapper(metric_fn, mask_index=-1, name=None, **kwargs)

   Bases: :py:obj:`tensorflow.keras.metrics.MeanMetricWrapper`


   .. py:method:: update_state(y_true, y_pred, sample_weight=None)


   .. py:attribute:: mask_index
      :value: -1



.. py:class:: LazySegmentationModel(base_model, ignore_channel_index=-1, **kwargs)

   Bases: :py:obj:`tensorflow.keras.Model`


   .. py:method:: call(*args, **kwargs)


   .. py:method:: compile(optimizer='rmsprop', loss=None, loss_weights=None, metrics=None, weighted_metrics=None, run_eagerly=False, steps_per_execution=1, jit_compile='auto', **kwargs)


   .. py:method:: evaluate(*args, **kwargs)


   .. py:method:: fit(*args, **kwargs)


   .. py:attribute:: base_unet


   .. py:attribute:: mask_index
      :value: -1



.. py:function:: pop_channel(tensor, channel_to_remove)