glitchgan.tf.model_components
=============================

.. py:module:: glitchgan.tf.model_components

.. autoapi-nested-parse::

   TensorFlow/Keras model components for cDVGAN.

   Architecture is identical to the original TF reference implementation.
   Lambda layers have been replaced with proper subclassed layers for
   compatibility with Keras 3 and correct model serialisation.









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

.. py:data:: NUM_CLASSES
   :value: 7


.. py:class:: ArgmaxLayer(*, activity_regularizer=None, trainable=True, dtype=None, autocast=True, name=None, **kwargs)

   Bases: :py:obj:`keras.layers.Layer`


   Return the argmax along the last axis as int32.


   .. py:method:: call(x)


.. py:class:: ReduceSumDotLayer(*, activity_regularizer=None, trainable=True, dtype=None, autocast=True, name=None, **kwargs)

   Bases: :py:obj:`keras.layers.Layer`


   Compute element-wise product and sum along axis 1 (keepdims).


   .. py:method:: call(inputs)


.. py:function:: get_discriminator_model(in_shape=8192, num_classes=NUM_CLASSES, print_summary=False)

.. py:function:: get_derivative_discriminator_model(in_shape=8191, num_classes=NUM_CLASSES, print_summary=False)

.. py:function:: get_second_derivative_discriminator_model(in_shape=8190, num_classes=NUM_CLASSES, print_summary=False)

.. py:function:: get_generator_model(noise_dim=100, num_classes=NUM_CLASSES, print_summary=False)