#include <sparse_ops.h>
The gradient of SparseFillEmptyRows.
Takes vectors reverse_index_map, shaped [N]
, and grad_values, shaped [N_full]
, where N_full >= N
and copies data into either d_values
or d_default_value
. Here d_values
is shaped [N]
and d_default_value
is a scalar.
d_values[j] = grad_values[reverse_index_map[j]] d_default_value = sum_{k : 0 .. N_full - 1} ( grad_values[k] * 1{k not in reverse_index_map})
Arguments:
Returns:
Output
d_values: 1-D. The backprop into values.Output
d_default_value: 0-D. The backprop into default_value. Constructors and Destructors | |
---|---|
SparseFillEmptyRowsGrad(const ::tensorflow::Scope & scope, ::tensorflow::Input reverse_index_map, ::tensorflow::Input grad_values) |
Public attributes | |
---|---|
d_default_value | |
d_values |
::tensorflow::Output d_default_value
::tensorflow::Output d_values
SparseFillEmptyRowsGrad( const ::tensorflow::Scope & scope, ::tensorflow::Input reverse_index_map, ::tensorflow::Input grad_values )
© 2017 The TensorFlow Authors. All rights reserved.
Licensed under the Creative Commons Attribution License 3.0.
Code samples licensed under the Apache 2.0 License.
https://www.tensorflow.org/api_docs/cc/class/tensorflow/ops/sparse-fill-empty-rows-grad.html