cellmap_flow.finetune.target_transforms
=======================================

.. py:module:: cellmap_flow.finetune.target_transforms

.. autoapi-nested-parse::

   Target transforms for converting user annotations to training targets.

   Each transform takes a raw annotation tensor (B, 1, Z, Y, X) with values:
     0 = unannotated (ignored in loss)
     1 = background
     2 = first foreground object
     3 = second foreground object, etc.

   And produces:
     target: (B, C, Z, Y, X) — training target matching model output channels
     mask: (B, C, Z, Y, X) or (B, 1, Z, Y, X) — valid loss mask



Classes
-------

.. autoapisummary::

   cellmap_flow.finetune.target_transforms.TargetTransform
   cellmap_flow.finetune.target_transforms.BinaryTargetTransform
   cellmap_flow.finetune.target_transforms.BroadcastBinaryTargetTransform
   cellmap_flow.finetune.target_transforms.AffinityTargetTransform


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

.. py:class:: TargetTransform

   Base class for target transforms.


.. py:class:: BinaryTargetTransform



   Standard binary segmentation transform (current default behavior).

   Produces single-channel binary target: bg=0, fg=1.
   Mask marks annotated regions.


.. py:class:: BroadcastBinaryTargetTransform(num_channels: int)



   Binary target broadcast to N channels.

   All output channels receive the same fg/bg target.
   Useful for treating multi-channel models (affinities, distances)
   as simple binary segmentation.


   .. py:attribute:: num_channels


.. py:class:: AffinityTargetTransform(offsets: List[List[int]], num_channels: int = None)



   Compute affinity targets from instance labels.

   For each offset, affinity is:
     1 if both voxels belong to the same foreground object (same label > 1)
     0 if different objects, or either is background

   The loss mask requires both voxels in each pair to be annotated (label > 0),
   producing a per-channel mask since each offset shifts differently.

   :param offsets: List of [dz, dy, dx] offset tuples defining neighbor relationships.
   :param num_channels: Total number of model output channels. If greater than
                        len(offsets), extra channels (e.g. LSDs) are masked out
                        (mask=0) so they receive no gradient. If None, defaults
                        to len(offsets).


   .. py:attribute:: offsets


   .. py:attribute:: num_channels