:py:mod:`evoaug_tf.evoaug`
==========================

.. py:module:: evoaug_tf.evoaug

.. autoapi-nested-parse::

   Model (implemented in Tensorflow) demonstrating how to use augmentations
   during training.



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

Classes
~~~~~~~

.. autoapisummary::

   evoaug_tf.evoaug.RobustModel



Functions
~~~~~~~~~

.. autoapisummary::

   evoaug_tf.evoaug.augment_max_len



.. py:class:: RobustModel(model_func, input_shape=None, augment_list=[], max_augs_per_seq=2, hard_aug=False, finetune=False, inference_aug=False, **kwargs)


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

   Tensorflow keras.Model to specify how augmentation should be applied to a model

   :param model: Keras model.
   :type model: keras.Model
   :param augment_list: List of data augmentations, each a callable class from augment.py
                        Default is empty list -- no augmentations.
   :type augment_list: list
   :param max_augs_per_seq: Maximum number of augmentations to apply to each sequence. Value is superceded by the number of augmentations in augment_list.
   :type max_augs_per_seq: int
   :param hard_aug: Flag to set a hard number of augmentations, otherwise the number of augmentations is set randomly up to max_augs_per_seq, default is True.
   :type hard_aug: bool
   :param finetune: Flag to turn off augmentations during training, default is False.
   :type finetune: bool
   :param inference_aug: Flag to turn on augmentations during inference, default is False.
   :type inference_aug: bool

   .. py:method:: build_model(input_shape)


   .. py:method:: call(inputs, training=False)


   .. py:method:: train_step(data)


   .. py:method:: test_step(batch)


   .. py:method:: predict_step(batch)


   .. py:method:: _apply_augment(x)

      Apply augmentations to each sequence in batch, x.


   .. py:method:: _pad_end(x)

      Add random DNA padding of length insert_max to the end of each sequence in batch.


   .. py:method:: finetune_mode(optimizer=None, lr=None)

      Turn on finetune flag -- no augmentations during training.


   .. py:method:: save_weights(filepath)


   .. py:method:: load_weights(filepath)



.. py:function:: augment_max_len(augment_list)

   Determine whether insertions are applied to determine the insert_max,
   which will be applied to pad other sequences with random DNA.
   :param augment_list: List of augmentations.
   :type augment_list: list

   :returns: Value for insert max.
   :rtype: int