Tune in to the first Women in ML Symposium this Tuesday, October 19 at 9am PST Register now

tensorflow:: ops:: SparseSoftmax

#include <sparse_ops.h>

Applies softmax to a batched N-D SparseTensor .

Summary

The inputs represent an N-D SparseTensor with logical shape [..., B, C] (where N >= 2 ), and with indices sorted in the canonical lexicographic order.

This op is equivalent to applying the normal tf.nn.softmax() to each innermost logical submatrix with shape [B, C] , but with the catch that the implicitly zero elements do not participate . Specifically, the algorithm is equivalent to the following:

(1) Applies tf.nn.softmax() to a densified view of each innermost submatrix with shape [B, C] , along the size-C dimension; (2) Masks out the original implicitly-zero locations; (3) Renormalizes the remaining elements.

Hence, the SparseTensor result has exactly the same non-zero indices and shape.

Args:

  • scope: A Scope object
  • sp_indices: 2-D. NNZ x R matrix with the indices of non-empty values in a SparseTensor, in canonical ordering.
  • sp_values: 1-D. NNZ non-empty values corresponding to sp_indices .
  • sp_shape: 1-D. Shape of the input SparseTensor.

Returns:

  • Output : 1-D. The NNZ values for the result SparseTensor .

Constructors and Destructors

SparseSoftmax (const :: tensorflow::Scope & scope, :: tensorflow::Input sp_indices, :: tensorflow::Input sp_values, :: tensorflow::Input sp_shape)

Public attributes

operation
output

Public functions

node () const
::tensorflow::Node *
operator::tensorflow::Input () const
operator::tensorflow::Output () const

Public attributes

operation

Operation operation

output

::tensorflow::Output output

Public functions

SparseSoftmax

 SparseSoftmax(
  const ::tensorflow::Scope & scope,
  ::tensorflow::Input sp_indices,
  ::tensorflow::Input sp_values,
  ::tensorflow::Input sp_shape
)

node

::tensorflow::Node * node() const 

operator::tensorflow::Input

 operator::tensorflow::Input() const 

operator::tensorflow::Output

 operator::tensorflow::Output() const