tf.raw_ops.SparseFillEmptyRowsGrad | TensorFlow v2.16.1 (original) (raw)
tf.raw_ops.SparseFillEmptyRowsGrad
Stay organized with collections Save and categorize content based on your preferences.
The gradient of SparseFillEmptyRows.
View aliases
Compat aliases for migration
SeeMigration guide for more details.
tf.compat.v1.raw_ops.SparseFillEmptyRowsGrad
tf.raw_ops.SparseFillEmptyRowsGrad(
reverse_index_map, grad_values, name=None
)
Takes vectors reverse_index_map, shaped [N], and grad_values, shaped [N_full], where N_full >= N and copies data into eitherd_values or d_default_value. Here d_values is shaped [N] andd_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})
| Args | |
|---|---|
| reverse_index_map | A Tensor of type int64. 1-D. The reverse index map from SparseFillEmptyRows. |
| grad_values | A Tensor. 1-D. The gradients from backprop. |
| name | A name for the operation (optional). |
| Returns | |
|---|---|
| A tuple of Tensor objects (d_values, d_default_value). | |
| d_values | A Tensor. Has the same type as grad_values. |
| d_default_value | A Tensor. Has the same type as grad_values. |