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})
Constants
String | OP_NAME | The name of this op, as known by TensorFlow core engine |
Public Methods
static <T extends TType> SparseFillEmptyRowsGrad<T> | |
Output<T> |
dDefaultValue()
0-D.
|
Output<T> |
dValues()
1-D.
|
Inherited Methods
Constants
public static final String OP_NAME
The name of this op, as known by TensorFlow core engine
Public Methods
public static SparseFillEmptyRowsGrad<T> create (Scope scope, Operand<TInt64> reverseIndexMap, Operand<T> gradValues)
Factory method to create a class wrapping a new SparseFillEmptyRowsGrad operation.
Parameters
scope | current scope |
---|---|
reverseIndexMap | 1-D. The reverse index map from SparseFillEmptyRows. |
gradValues | 1-D. The gradients from backprop. |
Returns
- a new instance of SparseFillEmptyRowsGrad