ML Community Day is November 9! Join us for updates from TensorFlow, JAX, and more Learn more

SparseMatrixSoftmax

public final class SparseMatrixSoftmax

Calculates the softmax of a CSRSparseMatrix.

Calculate the softmax of the innermost dimensions of a SparseMatrix.

Missing values are treated as `-inf` (i.e., logits of zero probability); and the output has the same sparsity structure as the input (though missing values in the output may now be treated as having probability zero).

Public Methods

Output<Object>
asOutput()
Returns the symbolic handle of a tensor.
static <T extends Number> SparseMatrixSoftmax
create(Scope scope, Operand<?> logits, Class<T> type)
Factory method to create a class wrapping a new SparseMatrixSoftmax operation.
Output<?>
softmax()
A CSRSparseMatrix.

Inherited Methods

Public Methods

public Output<Object> asOutput ()

Returns the symbolic handle of a tensor.

Inputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.

public static SparseMatrixSoftmax create (Scope scope, Operand<?> logits, Class<T> type)

Factory method to create a class wrapping a new SparseMatrixSoftmax operation.

Parameters
scope current scope
logits A CSRSparseMatrix.
Returns
  • a new instance of SparseMatrixSoftmax

public Output<?> softmax ()

A CSRSparseMatrix.