SparseSegmentSum

tensorflow C++ API

tensorflow::ops::SparseSegmentSum

Computes the sum along sparse segments of a tensor.

Summary

Read the section on segmentation for an explanation of segments.

LikeSegmentSum, butsegment_idscan have rank less thandata’s first dimension, selecting a subset of dimension 0, specified byindices.

For example:

```python c = tf.constant([[1,2,3,4], [-1,-2,-3,-4], [5,6,7,8]])

Select two rows, one segment.

tf.sparse_segment_sum(c, tf.constant([0, 1]), tf.constant([0, 0])) => [[0 0 0 0]]

Select two rows, two segment.

tf.sparse_segment_sum(c, tf.constant([0, 1]), tf.constant([0, 1])) => [[ 1 2 3 4]

[-1 -2 -3 -4]]

Select all rows, two segments.

tf.sparse_segment_sum(c, tf.constant([0, 1, 2]), tf.constant([0, 0, 1])) => [[0 0 0 0]

[5 6 7 8]]

Which is equivalent to:

tf.segment_sum(c, tf.constant([0, 0, 1])) ```

Arguments:

• scope: AScope object
• indices: A 1-D tensor. Has same rank as segment_ids.
• segment_ids: A 1-D tensor. Values should be sorted and can be repeated.

Returns:

• Output: Has same shape as data, except for dimension 0 which has sizek, the number of segments.

Constructor

• SparseSegmentSum(const ::tensorflow::Scope & scope, ::tensorflow::Input data, ::tensorflow::Input indices, ::tensorflow::Input segment_ids)

Public attributes

• tensorflow::Output output

SparseSegmentSum block

Source link : https://github.com/EXPNUNI/enuSpaceTensorflow/blob/master/enuSpaceTensorflow/tf_math.cpp

Argument:

• Scope scope : A Scope object(A scope is generated automatically each page. A scope is not connected.).
• Input data : connect Input node.
• Input indices : connect Input node.
• Input segment_ids: connect Input node.

Return:

• Output product : Output object of SparseSegmentSum class object.

Result:

• std::vector(Tensor) product_result : Returned object of executed result by calling session.

Using Method