.. index:: pair: struct; dnnl_batch_normalization_desc_t .. _doxid-structdnnl__batch__normalization__desc__t: struct dnnl_batch_normalization_desc_t ====================================== .. toctree:: :hidden: Overview ~~~~~~~~ A descriptor of a Batch Normalization operation. :ref:`More...` .. ref-code-block:: cpp :class: doxyrest-overview-code-block #include struct dnnl_batch_normalization_desc_t { // fields :ref:`dnnl_primitive_kind_t` :ref:`primitive_kind`; :ref:`dnnl_prop_kind_t` :ref:`prop_kind`; :ref:`dnnl_memory_desc_t` :ref:`data_desc`; :ref:`dnnl_memory_desc_t` :ref:`diff_data_desc`; :ref:`dnnl_memory_desc_t` :ref:`data_scaleshift_desc`; :ref:`dnnl_memory_desc_t` :target:`diff_data_scaleshift_desc`; :ref:`dnnl_memory_desc_t` :ref:`stat_desc`; float :ref:`batch_norm_epsilon`; unsigned :target:`flags`; }; .. _details-structdnnl__batch__normalization__desc__t: Detailed Documentation ~~~~~~~~~~~~~~~~~~~~~~ A descriptor of a Batch Normalization operation. Fields ------ .. index:: pair: variable; primitive_kind .. _doxid-structdnnl__batch__normalization__desc__t_1a9418b8e53dc1201d1f06cdf0152afe27: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`dnnl_primitive_kind_t` primitive_kind The kind of primitive. Used for self-identifying the primitive descriptor. Must be :ref:`dnnl_batch_normalization `. .. index:: pair: variable; prop_kind .. _doxid-structdnnl__batch__normalization__desc__t_1a76acc806f760eea2589c375fdc8b80b1: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`dnnl_prop_kind_t` prop_kind The kind of propagation. Possible values: :ref:`dnnl_forward_training `, :ref:`dnnl_forward_inference `, :ref:`dnnl_backward `, and :ref:`dnnl_backward_data `. .. index:: pair: variable; data_desc .. _doxid-structdnnl__batch__normalization__desc__t_1a0f6463524bea1389a89ff67accd07d68: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`dnnl_memory_desc_t` data_desc Source and destination memory descriptor. .. index:: pair: variable; diff_data_desc .. _doxid-structdnnl__batch__normalization__desc__t_1a7aec0325ac47e3327aa506e2f7636c8f: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`dnnl_memory_desc_t` diff_data_desc Source and destination gradient memory descriptor. .. index:: pair: variable; data_scaleshift_desc .. _doxid-structdnnl__batch__normalization__desc__t_1a452eaa4f7413e5638c814304ee8819bc: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`dnnl_memory_desc_t` data_scaleshift_desc Scale and shift data and gradient memory descriptors. Scaleshift memory descriptor uses 2D :ref:`dnnl_nc ` format[2,Channels]. 1-st dimension contains gamma parameter, 2-nd dimension contains beta parameter. .. index:: pair: variable; stat_desc .. _doxid-structdnnl__batch__normalization__desc__t_1a5e779c209cd4296445ce2be9b6d5fbb8: .. ref-code-block:: cpp :class: doxyrest-title-code-block :ref:`dnnl_memory_desc_t` stat_desc Statistics memory descriptor. Statistics (mean or variance) descriptor use 1D :ref:`dnnl_x ` format[Channels]. .. index:: pair: variable; batch_norm_epsilon .. _doxid-structdnnl__batch__normalization__desc__t_1ab2508100481c6a19566f122198294e55: .. ref-code-block:: cpp :class: doxyrest-title-code-block float batch_norm_epsilon Batch normalization epsilon parameter.