:mod:`blueoil.networks.classification.quantize_example`
=======================================================

.. py:module:: blueoil.networks.classification.quantize_example


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

Classes
~~~~~~~

.. autoapisummary::

   blueoil.networks.classification.quantize_example.SampleNetwork
   blueoil.networks.classification.quantize_example.SampleNetworkQuantize



.. py:class:: SampleNetwork(*args, **kwargs)

   Bases: :class:`blueoil.networks.classification.base.Base`

   Sample network with simple layer.

   .. method:: base(self, images, is_training)

      Base function contains inference.

      :param images: Input images.
      :param is_training: A flag for if is training.

      :returns: Inference result.
      :rtype: tf.Tensor



.. py:class:: SampleNetworkQuantize(quantize_first_convolution=True, quantize_last_convolution=True, activation_quantizer=None, activation_quantizer_kwargs={}, weight_quantizer=None, weight_quantizer_kwargs={}, *args, **kwargs)

   Bases: :class:`blueoil.networks.classification.quantize_example.SampleNetwork`

   Quantize Sample Network.

   .. method:: _quantized_variable_getter(weight_quantization, quantize_first_convolution, quantize_last_convolution, getter, name, *args, **kwargs)
      :staticmethod:

      Get the quantized variables.

      Use if to choose or skip the target should be quantized.

      :param weight_quantization: Callable object which quantize variable.
      :param quantize_first_convolution: Use quantization in first conv.
      :type quantize_first_convolution: bool
      :param quantize_last_convolution: Use quantization in last conv.
      :type quantize_last_convolution: bool
      :param getter: Default from tensorflow.
      :param name: Default from tensorflow.
      :param args: Args.
      :param kwargs: Kwargs.


   .. method:: base(self, images, is_training)

      Base function contains inference.

      :param images: Input images.
      :param is_training: A flag for if is training.

      :returns: Inference result.
      :rtype: tf.Tensor