Computes gradients for SparseSegmentMean.
tf.raw_ops.SparseSegmentMeanGrad(
grad, indices, segment_ids, output_dim0, name=None
)
Returns tensor "output" with same shape as grad, except for dimension 0 whose value is output_dim0.
Args | |
|---|---|
grad
|
A Tensor. Must be one of the following types: bfloat16, half, float32, float64.
gradient propagated to the SparseSegmentMean op.
|
indices
|
A Tensor. Must be one of the following types: int32, int64.
indices passed to the corresponding SparseSegmentMean op.
|
segment_ids
|
A Tensor. Must be one of the following types: int32, int64.
segment_ids passed to the corresponding SparseSegmentMean op.
|
output_dim0
|
A Tensor of type int32.
dimension 0 of "data" passed to SparseSegmentMean op.
|
name
|
A name for the operation (optional). |
Returns | |
|---|---|
A Tensor. Has the same type as grad.
|