.. _op_ai_onnx_SequenceConstruct:

SequenceConstruct
=================

- **Domain**: ``ai.onnx``
- **Since version**: 11

Construct a tensor sequence containing 'inputs' tensors.
All tensors in 'inputs' must have the same data type.

**Inputs**

- **inputs** (*T*): Tensors.

**Outputs**

- **output_sequence** (*S*): Sequence enclosing the input tensors.

**Type Constraints**

- **T**: Constrain input types 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).
- **S**: Constrain output types 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)).

Examples
--------

**test_cc_sequence_construct**

.. code-block:: text

    Inputs:
      a: shape=(2, 3), dtype=float32
        [[-1.  ,  0.  ,  1.5 ],
         [-2.25,  3.5 , -4.75]]
      b: shape=(2, 3), dtype=float32
        [[0., 1., 2.],
         [3., 4., 5.]]
      c: shape=(2, 3), dtype=float32
        [[ 6.,  7.,  8.],
         [ 9., 10., 11.]]

    Outputs:
      output_sequence: shape=(3, 2, 3), dtype=float32
        [[[-1.  ,  0.  ,  1.5 ],
          [-2.25,  3.5 , -4.75]],
        
         [[ 0.  ,  1.  ,  2.  ],
          [ 3.  ,  4.  ,  5.  ]],
        
         [[ 6.  ,  7.  ,  8.  ],
          [ 9.  , 10.  , 11.  ]]]

**test_cc_sequence_construct_int64_single**

.. code-block:: text

    Inputs:
      a: shape=(4,), dtype=int64
        [-1,  0,  1,  2]

    Outputs:
      output_sequence: shape=(1, 4), dtype=int64
        [[-1,  0,  1,  2]]