tf.sparse.segment_mean | TensorFlow v2.16.1 (original) (raw)
tf.sparse.segment_mean
Computes the mean along sparse segments of a tensor.
tf.sparse.segment_mean(
data,
indices,
segment_ids,
num_segments=None,
name=None,
sparse_gradient=False
)
Read the section on segmentationfor an explanation of segments.
Like tf.math.segment_mean, but segment_ids can have rank less thandata's first dimension, selecting a subset of dimension 0, specified byindices.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.
| 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 assegment_ids. |
| segment_ids | A 1-D Tensor with indices into the output Tensor. Values should be sorted and can be repeated. |
| num_segments | An optional int32 scalar. Indicates the size of the outputTensor. |
| name | A name for the operation (optional). |
| sparse_gradient | An optional bool. Defaults to False. If True, the gradient of this function will be sparse (IndexedSlices) instead of dense (Tensor). The sparse gradient will contain one non-zero row for each unique index in indices. |
| 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. |
Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates. Some content is licensed under the numpy license.
Last updated 2024-04-26 UTC.