Skip to content

sparse_segment_sum.md

Latest commit

 

History

History
62 lines (44 loc) · 1.68 KB

sparse_segment_sum.md

File metadata and controls

62 lines (44 loc) · 1.68 KB

tfra.dynamic_embedding.math.sparse_segment_sum

View source on GitHub




Computes the sum along sparse segments of a tensor. It do same things

tfra.dynamic_embedding.math.sparse_segment_sum(
    data,
    indices,
    segment_ids,
    name=None,
    num_segments=None
)

as tf.sparse.segment_sum. Here we provide GPU impl.

Go tf api for more details.

Args:

  • data: A Tensor with data that will be assembled in the output.
  • indices: A 1-D Tensor with indices into data. Has same rank as segment_ids.
  • segment_ids: A 1-D Tensor with indices into the output Tensor. Values should be sorted and can be repeated.
  • name: A name for the operation (optional).
  • num_segments: An optional int32 scalar. Indicates the size of the output Tensor.

Returns:

A tensor of the shape as data, except for dimension 0 which has size k, the number of segments specified via num_segments or inferred for the last element in segments_ids.