Computes the sum along sparse segments of a tensor.
tf.raw_ops.SparseSegmentSum(
data, indices, segment_ids, name=None
)
Read the section on segmentation for an explanation of segments.
Like SegmentSum
, but segment_ids
can have rank less than data
's first
dimension, selecting a subset of dimension 0, specified by indices
.
For example:
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]))
Returns | |
---|---|
A Tensor . Has the same type as data .
|