Reverses variable length slices.
This op first slices `input` along the dimension `batch_dim`, and for each slice `i`, reverses the first `seq_lengths[i]` elements along the dimension `seq_dim`.
The elements of `seq_lengths` must obey `seq_lengths[i] <= input.dims[seq_dim]`, and `seq_lengths` must be a vector of length `input.dims[batch_dim]`.
The output slice `i` along dimension `batch_dim` is then given by input slice `i`, with the first `seq_lengths[i]` slices along dimension `seq_dim` reversed.
For example:
# Given this:
batch_dim = 0
seq_dim = 1
input.dims = (4, 8, ...)
seq_lengths = [7, 2, 3, 5]
# then slices of input are reversed on seq_dim, but only up to seq_lengths:
output[0, 0:7, :, ...] = input[0, 7:0:-1, :, ...]
output[1, 0:2, :, ...] = input[1, 2:0:-1, :, ...]
output[2, 0:3, :, ...] = input[2, 3:0:-1, :, ...]
output[3, 0:5, :, ...] = input[3, 5:0:-1, :, ...]
# while entries past seq_lens are copied through:
output[0, 7:, :, ...] = input[0, 7:, :, ...]
output[1, 2:, :, ...] = input[1, 2:, :, ...]
output[2, 3:, :, ...] = input[2, 3:, :, ...]
output[3, 2:, :, ...] = input[3, 2:, :, ...]
In contrast, if:
# Given this:
batch_dim = 2
seq_dim = 0
input.dims = (8, ?, 4, ...)
seq_lengths = [7, 2, 3, 5]
# then slices of input are reversed on seq_dim, but only up to seq_lengths:
output[0:7, :, 0, :, ...] = input[7:0:-1, :, 0, :, ...]
output[0:2, :, 1, :, ...] = input[2:0:-1, :, 1, :, ...]
output[0:3, :, 2, :, ...] = input[3:0:-1, :, 2, :, ...]
output[0:5, :, 3, :, ...] = input[5:0:-1, :, 3, :, ...]
# while entries past seq_lens are copied through:
output[7:, :, 0, :, ...] = input[7:, :, 0, :, ...]
output[2:, :, 1, :, ...] = input[2:, :, 1, :, ...]
output[3:, :, 2, :, ...] = input[3:, :, 2, :, ...]
output[2:, :, 3, :, ...] = input[2:, :, 3, :, ...]
Nested Classes
class | ReverseSequence.Options | Optional attributes for ReverseSequence
|
Public Methods
Output<T> |
asOutput()
Returns the symbolic handle of a tensor.
|
static ReverseSequence.Options |
batchDim(Long batchDim)
|
static <T, U extends Number> ReverseSequence<T> |
create(Scope scope, Operand<T> input, Operand<U> seqLengths, Long seqDim, Options... options)
Factory method to create a class wrapping a new ReverseSequence operation.
|
Output<T> |
output()
The partially reversed input.
|
Inherited Methods
Public Methods
public Output<T> asOutput ()
Returns the symbolic handle of a tensor.
Inputs 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.
public static ReverseSequence.Options batchDim (Long batchDim)
Parameters
batchDim | The dimension along which reversal is performed. |
---|
public static ReverseSequence<T> create (Scope scope, Operand<T> input, Operand<U> seqLengths, Long seqDim, Options... options)
Factory method to create a class wrapping a new ReverseSequence operation.
Parameters
scope | current scope |
---|---|
input | The input to reverse. |
seqLengths | 1-D with length `input.dims(batch_dim)` and `max(seq_lengths) <= input.dims(seq_dim)` |
seqDim | The dimension which is partially reversed. |
options | carries optional attributes values |
Returns
- a new instance of ReverseSequence