:mod:`blueoil.networks.segmentation.lm_segnet_v0` ================================================= .. py:module:: blueoil.networks.segmentation.lm_segnet_v0 Module Contents --------------- Classes ~~~~~~~ .. autoapisummary:: blueoil.networks.segmentation.lm_segnet_v0.LmSegnetV0 blueoil.networks.segmentation.lm_segnet_v0.LmSegnetV0Quantize .. py:class:: LmSegnetV0(*args, **kwargs) Bases: :class:`blueoil.networks.segmentation.base.SegnetBase` LM customized SegNet Network. .. method:: _get_lmnet_block(self, is_training, channels_data_format) .. method:: _max_pool_with_argmax(self, inputs=None, ksize=None, strides=None, padding=None, name='') .. method:: _unpool_with_argmax(self, inputs=None, mask=None, ksize=None, name='') .. method:: base(self, images, is_training, *args, **kwargs) 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:: LmSegnetV0Quantize(activation_quantizer=None, activation_quantizer_kwargs={}, weight_quantizer=None, weight_quantizer_kwargs={}, *args, **kwargs) Bases: :class:`blueoil.networks.segmentation.lm_segnet_v0.LmSegnetV0` LM customized Segnet quantize network. Following `args` are used for inference: ``activation_quantizer``, ``activation_quantizer_kwargs``, ``weight_quantizer``, ``weight_quantizer_kwargs``. :param activation_quantizer: Weight quantizater. See more at `blueoil.quantizations`. :type activation_quantizer: callable :param activation_quantizer_kwargs: Kwargs for `activation_quantizer`. :type activation_quantizer_kwargs: dict :param weight_quantizer: Activation quantizater. See more at `blueoil.quantizations`. :type weight_quantizer: callable :param weight_quantizer_kwargs: Kwargs for `weight_quantizer`. :type weight_quantizer_kwargs: dict .. method:: _quantized_variable_getter(getter, name, weight_quantization=None, *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.