SparseSegmentMeanGrad

tensorflow C++ API

tensorflow::ops::SparseSegmentMeanGrad

Computes gradients for SparseSegmentMean.

Summary

Returns tensor “output” with same shape as grad, except for dimension 0 whose value is output_dim0.

Arguments:

• scope: AScope object
• grad: gradient propagated to the SparseSegmentMean op.
• indices: indices passed to the corresponding SparseSegmentMean op.
• segment_ids: segment_ids passed to the corresponding SparseSegmentMean op.
• output_dim0: dimension 0 of “data” passed to SparseSegmentMean op.

Returns:

• Output: The output tensor.

Constructor

• SparseSegmentMeanGrad(const ::tensorflow::Scope & scope, ::tensorflow::Input grad, ::tensorflow::Input indices, ::tensorflow::Input segment_ids, ::tensorflow::Input output_dim0)

Public attributes

• tensorflow::Output output

SparseSegmentMeanGrad 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 indices : connect Input node.
• Input segment_ids : connect Input node.
• Input output_dim0 : connect Input node.

Return:

• Output product : Output object of SparseSegmentMeanGrad class object.

Result:

• std::vector(Tensor) product_result : Returned object of executed result by calling session.

Using Method