:nosearch:

.. _op_ai_onnx_Upsample-1:

Upsample - version 1
====================

This page documents version **1** of operator **Upsample**. See :doc:`Upsample` for the latest version (since version 10).

- **Domain**: ``ai.onnx``
- **Since version**: 1

Upsample the input tensor.
The width and height of the output tensor are:

.. code-block:: text

    output_width = floor(input_width * width_scale),
    output_height = floor(input_height * height_scale).

Example:

.. code-block:: text

    Given `data` tensor, width_scale, height_scale, mode,
    Upsample the input 4-D tensor in nearest mode:
    data = [[[
        [1, 2],
        [3, 4]
    ]]]
    width_scale = 2
    height_scale = 2
    mode = "nearest"
    output = [[[
        [1, 1, 2, 2],
        [1, 1, 2, 2],
        [3, 3, 4, 4],
        [3, 3, 4, 4]
    ]]]


**Inputs**

- **X** (*T*): 4-D tensor, [N,C,H,W]

**Outputs**

- **Y** (*T*): 4-D tensor after resizing, [N,C,H,W]

**Attributes**

- **height_scale** (*float*): The scale along height dimension. It takes value greater than or equal to 1.
- **mode** (*string*): Two interpolation modes: nearest(default), bilinear
- **width_scale** (*float*): The scale along width dimension. It takes value greater than or equal to 1.

**Type Constraints**

- **T**: Constrain output types to bool, int32, int64, float16, float, double tensors.
  Allowed types: tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64).