@Operator public final class TensorListScatterV2 extends PrimitiveOp implements Operand<Object>
Each member of the TensorList corresponds to one row of the input tensor, specified by the given index (see `tf.gather`).
tensor: The input tensor. indices: The indices used to index into the list. element_shape: The shape of the elements in the list (can be less specified than the shape of the tensor). num_elements: The size of the output list. Must be large enough to accommodate the largest index in indices. If -1, the list is just large enough to include the largest index in indices. output_handle: The TensorList.
operation| Modifier and Type | Method and Description |
|---|---|
Output<Object> |
asOutput()
Returns the symbolic handle of a tensor.
|
static <T,U extends Number> |
create(Scope scope,
Operand<T> tensor,
Operand<Integer> indices,
Operand<U> elementShape,
Operand<Integer> numElements)
Factory method to create a class wrapping a new TensorListScatterV2 operation.
|
Output<?> |
outputHandle() |
equals, hashCode, op, toStringpublic static <T,U extends Number> TensorListScatterV2 create(Scope scope, Operand<T> tensor, Operand<Integer> indices, Operand<U> elementShape, Operand<Integer> numElements)
scope - current scopetensor - indices - elementShape - numElements - public Output<?> outputHandle()
public Output<Object> asOutput()
OperandInputs to TensorFlow operations are outputs of another TensorFlow operation. This method is used to obtain a symbolic handle that represents the computation of the input.
asOutput in interface Operand<Object>OperationBuilder.addInput(Output)Copyright © 2015–2019. All rights reserved.