SequenceAt#

Domain: ai.onnx
Since version: 11

Outputs a tensor copy from the tensor at ‘position’ in ‘input_sequence’. Accepted range for ‘position’ is in [-n, n - 1], where n is the number of tensors in ‘input_sequence’. Negative value means counting positions from the back.

Inputs

input_sequence (S): Input sequence.
position (I): Position of the tensor in the sequence. Negative value means counting positions from the back. Accepted range in [-n, n - 1], where n is the number of tensors in ‘input_sequence’. It is an error if any of the index values are out of bounds. It must be a scalar(tensor of empty shape).

Outputs

tensor (T): Output tensor at the specified position in the input sequence.

Type Constraints

S: Constrain to any tensor type. Allowed types: seq(tensor(bool)), seq(tensor(complex128)), seq(tensor(complex64)), seq(tensor(double)), seq(tensor(float)), seq(tensor(float16)), seq(tensor(int16)), seq(tensor(int32)), seq(tensor(int64)), seq(tensor(int8)), seq(tensor(string)), seq(tensor(uint16)), seq(tensor(uint32)), seq(tensor(uint64)), seq(tensor(uint8)).
T: Constrain to any tensor type. Allowed types: tensor(bool), tensor(complex128), tensor(complex64), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8).
I: Constrain position to integral tensor. It must be a scalar(tensor of empty shape). Allowed types: tensor(int32), tensor(int64).

Examples#

test_cc_sequence_at_neg

Node:
  SequenceAt(input_seq, position) -> (output_tensor)

Inputs:
  input_seq: shape=(2, 3), dtype=float32
    [[-1.  ,  0.  ,  1.5 ],
     [-2.25,  3.5 , -4.75]]
  position: shape=(2, 3), dtype=float32
    [[0., 1., 2.],
     [3., 4., 5.]]
  input_2: shape=(2, 3), dtype=float32
    [[ 6.,  7.,  8.],
     [ 9., 10., 11.]]
  input_3: shape=(), dtype=int64
    -2

Outputs:
  output_tensor: shape=(2, 3), dtype=float32
    [[0., 1., 2.],
     [3., 4., 5.]]

test_cc_sequence_at_pos0

Node:
  SequenceAt(input_seq, position) -> (output_tensor)

Inputs:
  input_seq: shape=(2, 3), dtype=float32
    [[-1.  ,  0.  ,  1.5 ],
     [-2.25,  3.5 , -4.75]]
  position: shape=(2, 3), dtype=float32
    [[0., 1., 2.],
     [3., 4., 5.]]
  input_2: shape=(2, 3), dtype=float32
    [[ 6.,  7.,  8.],
     [ 9., 10., 11.]]
  input_3: shape=(), dtype=int64
    0

Outputs:
  output_tensor: shape=(2, 3), dtype=float32
    [[-1.  ,  0.  ,  1.5 ],
     [-2.25,  3.5 , -4.75]]

test_cc_sequence_at_pos2

Node:
  SequenceAt(input_seq, position) -> (output_tensor)

Inputs:
  input_seq: shape=(2, 3), dtype=float32
    [[-1.  ,  0.  ,  1.5 ],
     [-2.25,  3.5 , -4.75]]
  position: shape=(2, 3), dtype=float32
    [[0., 1., 2.],
     [3., 4., 5.]]
  input_2: shape=(2, 3), dtype=float32
    [[ 6.,  7.,  8.],
     [ 9., 10., 11.]]
  input_3: shape=(), dtype=int64
    2

Outputs:
  output_tensor: shape=(2, 3), dtype=float32
    [[ 6.,  7.,  8.],
     [ 9., 10., 11.]]