:py:mod:`orcanet.builder_util.builders`
=======================================

.. py:module:: orcanet.builder_util.builders


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

Classes
~~~~~~~

.. autoapisummary::

   orcanet.builder_util.builders.BlockBuilder



Functions
~~~~~~~~~

.. autoapisummary::

   orcanet.builder_util.builders.get_input_block



.. py:class:: BlockBuilder(defaults=None, verbose=False, input_opts=None, **kwargs)

   
   Builds single-input block-wise sequential neural network.


   :Parameters:

       **defaults** : dict or None
           Default values for all blocks in the model.

       **verbose** : bool
           Print info about the building process?

       **batch_size** : int, optional
           Define a fixed batchsize for the input.














   ..
       !! processed by numpydoc !!
   .. py:method:: build(input_shape, configs)

      
      Build the whole model, using the default values when arguments
      are missing in the layer_configs.


      :Parameters:

          **input_shape** : dict
              Name and shape of the input layer.

          **configs** : list
              List of configurations for the blocks in the model.
              Each element in the list is a dict and will result in one block
              connected to the previous one. The dict has to contain the type
              of the block, as well as any arguments required by that
              specific block type.

      :Returns:

          **model** : keras model
              ..













      ..
          !! processed by numpydoc !!

   .. py:method:: attach_block(layer, layer_config)

      
      Attach a block to the given layer based on the layer config.

      Will use the default values given during initialization if they are not
      present in the layer config.

      :Parameters:

          **layer** : keras layer
              Layer to attach the block to.

          **layer_config** : dict
              Configuration of the block to attach. The dict has to contain
              the type of the block, as well as any arguments required by that
              specific block.

      :Returns:

          keras layer
              ..













      ..
          !! processed by numpydoc !!


.. py:function:: get_input_block(input_shapes, batchsize=None, names=None)

   
   Build input layers according to a dict mapping the layer names to shapes.
   If none appears in shape, input is ragged.


   :Parameters:

       **input_shapes** : dict
           Keys: Input layer names.
           Values: Their shapes.

       **batchsize** : int, optional
           Specify fixed batchsize.

       **names** : tuple, optional
           Make sure the inputs are these names and return them in this order.

   :Returns:

       **inputs** : tf.Tensor or tuple
           A list of named keras input layers, or the input Tensor if there
           is only one input.













   ..
       !! processed by numpydoc !!