SegmentMax

public final class SegmentMax

Computes the maximum along segments of a tensor.

Read [the section on segmentation](https://tensorflow.org/api_docs/python/tf/math#Segmentation) for an explanation of segments.

Computes a tensor such that \\(output_i = \max_j(data_j)\\) where `max` is over `j` such that `segment_ids[j] == i`.

If the max is empty for a given segment ID `i`, `output[i] = 0`.

For example:

c = tf.constant([[1,2,3,4], [4, 3, 2, 1], [5,6,7,8]])
 tf.segment_max(c, tf.constant([0, 0, 1]))
 # ==> [[4, 3, 3, 4],
 #      [5, 6, 7, 8]]
 

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> SegmentMax<T>
create(Scope scope, Operand<T> data, Operand<? extends TNumber> segmentIds)
Factory method to create a class wrapping a new SegmentMax 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: "SegmentMax"

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 SegmentMax<T> create (Scope scope, Operand<T> data, Operand<? extends TNumber> segmentIds)

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

Parameters
scope current scope
segmentIds A 1-D tensor whose size is equal to the size of `data`'s first dimension. Values should be sorted and can be repeated.
Returns
  • a new instance of SegmentMax

public Output<T> output ()

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