:mod:`blueoil.networks.object_detection.yolo_v2_quantize`
=========================================================

.. py:module:: blueoil.networks.object_detection.yolo_v2_quantize


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

Classes
~~~~~~~

.. autoapisummary::

   blueoil.networks.object_detection.yolo_v2_quantize.YoloV2Quantize



.. py:class:: YoloV2Quantize(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.object_detection.yolo_v2.YoloV2`

   Quantize YOLOv2 Network.

   It is based on original YOLO v2.

   .. 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 getter: Default from tensorflow.
      :param name: Default from tensorflow.
      :param weight_quantization: Callable object which quantize variable.
      :param args: Args.
      :param kwargs: Kwargs.


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

      Base network.

      Returns: Output. output shape depends on parameter.
          When `data_format` is `NHWC`
          shape is [
              batch_size,
              num_cell[0],
              num_cell[1],
              (num_classes + 5(x, y ,w, h, confidence)) * boxes_per_cell(length of anchors),
          ]

          When `data_format` is `NCHW`
          shape is [
              batch_size,
              (num_classes + 5(x, y ,w, h, confidence)) * boxes_per_cell(length of anchors),
              num_cell[0],
              num_cell[1],
          ]