SegmentMean
tensorflow C++ API
Computes the mean along segments of a tensor.
Summary
Read the section on segmentation for an explanation of segments.
Computes a tensor such that output_i = { data_j}{N} wheremean
is overj
such thatsegment_ids[j] == i
andN
is the total number of values summed.
If the mean is empty for a given segment IDi
,output[i] = 0
.
Arguments:
- scope: A Scope object
- segment_ids: A 1-D tensor whose rank is equal to the rank of data’s first dimension. 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
- SegmentMean(const ::tensorflow::Scope & scope, ::tensorflow::Input data, ::tensorflow::Input segment_ids)
Public attributes
- tensorflow::Output output.
SegmentMean 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 segment_ids:connect Input node.
Return:
- Output output: Output object of SegmentMean class object.
Result:
- std::vector(Tensor) product_result : Returned object of executed result by calling session.