T
- data type for outputValues()
output@Operator(group="sparse") public final class SparseSplit<T> extends PrimitiveOp
If the `shape[split_dim]` is not an integer multiple of `num_split`. Slices `[0 : shape[split_dim] % num_split]` gets one extra dimension. For example, if `split_dim = 1` and `num_split = 2` and the input is
input_tensor = shape = [2, 7] [ a d e ] [b c ]
Graphically the output tensors are:
output_tensor[0] = shape = [2, 4] [ a ] [b c ]
output_tensor[1] = shape = [2, 3] [ d e ] [ ]
operation
Modifier and Type | Method and Description |
---|---|
static <T> SparseSplit<T> |
create(Scope scope,
Operand<Long> splitDim,
Operand<Long> indices,
Operand<T> values,
Operand<Long> shape,
Long numSplit)
Factory method to create a class wrapping a new SparseSplit operation.
|
List<Output<Long>> |
outputIndices() |
List<Output<Long>> |
outputShape()
A list of 1-D tensors represents the shape of the output sparse
tensors.
|
List<Output<T>> |
outputValues()
A list of 1-D tensors represents the values of the output sparse
tensors.
|
equals, hashCode, op, toString
public static <T> SparseSplit<T> create(Scope scope, Operand<Long> splitDim, Operand<Long> indices, Operand<T> values, Operand<Long> shape, Long numSplit)
scope
- current scopesplitDim
- 0-D. The dimension along which to split. Must be in the range
`[0, rank(shape))`.indices
- 2-D tensor represents the indices of the sparse tensor.values
- 1-D tensor represents the values of the sparse tensor.shape
- 1-D. tensor represents the shape of the sparse tensor.
output indices: A list of 1-D tensors represents the indices of the output
sparse tensors.numSplit
- The number of ways to split.public List<Output<T>> outputValues()
Copyright © 2022. All rights reserved.