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

SparseMatrixSoftmaxGrad

public final class SparseMatrixSoftmaxGrad

Calculates the gradient of the SparseMatrixSoftmax op.

Public Methods

Output<Object>
asOutput()
Returns the symbolic handle of a tensor.
static <T extends Number> SparseMatrixSoftmaxGrad
create(Scope scope, Operand<?> softmax, Operand<?> gradSoftmax, Class<T> type)
Factory method to create a class wrapping a new SparseMatrixSoftmaxGrad operation.
Output<?>
gradient()
The output gradient.

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 SparseMatrixSoftmaxGrad create (Scope scope, Operand<?> softmax, Operand<?> gradSoftmax, Class<T> type)

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

Parameters
scope current scope
softmax A CSRSparseMatrix.
gradSoftmax The gradient of `softmax`.
Returns
  • a new instance of SparseMatrixSoftmaxGrad

public Output<?> gradient ()

The output gradient.