|View source on GitHub|
Computes the mean along sparse segments of a tensor.
tf.sparse.segment_mean( data, indices, segment_ids, num_segments=None, name=None )
Read the section on segmentation for an explanation of segments.
segment_ids can have rank less than
data's first dimension, selecting a subset of dimension 0, specified by
segment_ids is allowed to have missing ids, in which case the output will
be zeros at those indices. In those cases
num_segments is used to determine
the size of the output.
Tensorwith data that will be assembled in the output.
indices: A 1-D
Tensorwith indices into
data. Has same rank as
segment_ids: A 1-D
Tensorwith indices into the output
Tensor. Values should be sorted and can be repeated.
num_segments: An optional int32 scalar. Indicates the size of the output
name: A name for the operation (optional).
tensor of the shape as data, except for dimension 0 which
k, the number of segments specified via
inferred for the last element in