SparseSegmentMean

public final class SparseSegmentMean

Computes the mean along sparse segments of a tensor.

See tf.sparse.segment_sum for usage examples.

Like `SegmentMean`, but `segment_ids` can have rank less than `data`'s first dimension, selecting a subset of dimension 0, specified by `indices`.

Constants

String OP_NAME The name of this op, as known by TensorFlow core engine

Public Methods

Output<T>
asOutput()
Returns the symbolic handle of the tensor.
static <T extends TNumber> SparseSegmentMean<T>
create(Scope scope, Operand<T> data, Operand<? extends TNumber> indices, Operand<? extends TNumber> segmentIds)
Factory method to create a class wrapping a new SparseSegmentMean operation.
Output<T>
output()
Has same shape as data, except for dimension 0 which has size `k`, the number of segments.

Inherited Methods

Constants

public static final String OP_NAME

The name of this op, as known by TensorFlow core engine

Constant Value: "SparseSegmentMean"

Public Methods

public Output<T> asOutput ()

Returns the symbolic handle of the 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 SparseSegmentMean<T> create (Scope scope, Operand<T> data, Operand<? extends TNumber> indices, Operand<? extends TNumber> segmentIds)

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

Parameters
scope current scope
indices A 1-D tensor. Has same rank as `segment_ids`.
segmentIds A 1-D tensor. Values should be sorted and can be repeated.
Returns
  • a new instance of SparseSegmentMean

public Output<T> output ()

Has same shape as data, except for dimension 0 which has size `k`, the number of segments.