.. index:: pair: page; Softmax .. _doxid-dev_guide_op_softmax: Softmax ======= General ~~~~~~~ Softmax operation applies following formula on every element of :math:`\src` tensor (the variable names follow the standard :ref:`Naming Conventions `): .. math:: dst_i = \frac{exp(src_i)}{\sum_{j=1}^{C} exp(src_j)} where :math:`C` is a size of tensor along axis dimension. Operation attributes ~~~~~~~~~~~~~~~~~~~~ ================================================================================================================= ======================================================== ==== ======================================== ========= Attribute Name Descr ================================================================================================================= ======================================================== ==== ======================================== ========= :ref:`axis ` Represents the axis of which the Softmax is calculated. s64 Arbitrary s64 value ( ``1`` in default) Optional ================================================================================================================= ======================================================== ==== ======================================== ========= Execution arguments ~~~~~~~~~~~~~~~~~~~ The inputs and outputs must be provided according to below index order when constructing an operation. Inputs ------ ====== ======== ========= Index Argu ====== ======== ========= 0 ``src`` Required ====== ======== ========= Outputs ------- ====== ======== ========= Index Argu ====== ======== ========= 0 ``dst`` Required ====== ======== ========= Supported data types ~~~~~~~~~~~~~~~~~~~~ Softmax operation supports the following data type combinations. ===== ===== Src D ===== ===== f32 f32 bf16 bf16 f16 f16 ===== =====