mindspore.ops.UpsampleTrilinear3D

View Source On Gitee
class mindspore.ops.UpsampleTrilinear3D(align_corners=False)[source]

Performs upsampling with trilinear interpolation across 3dims for 5dim input Tensor.

This operator scale up the volumetric input with specified output_size or scales factors, using trilinear upscaling algorithm.

Note

One of scales and output_size must be specified. And it is an error if both are specified.

Parameters

align_corners (bool, optional) – An optional bool. Default: False. If True, the input and output tensors are aligned by the center points of their corner pixels, preserving the values at the corner pixels. If False , the input and output tensors are aligned by the corner points of their corner pixels, and the interpolation use edge value padding for out of boundary values.

Inputs:

  • x (Tensor) - 5D tensor of shape \((N, C, D_{in}, H_{in}, W_{in})\). Supporting types: [float16, float32, float64].

  • output_size (Union[tuple[int], list[int]]): A tuple or list of 3 int elements \((output\_depth, output\_height, output\_width)\). Default: None.

  • scales (Union[tuple[float], list[float]]): A tuple or list of 3 float elements \((scale\_depth, scale\_height, scale\_width)\). Default: None.

Outputs:

  • y (Tensor) - Upsampled output with the same data type as x, whose shape is \((N, C, D_{out}, H_{out}, W_{out})\).

Raises

  • TypeError – When output_size is not None and output_size is not list[int] or tuple[int].

  • TypeError – When scales is not None and scales is not list[float] or tuple[float].

  • TypeError – If dtype of x is not in [float16, float32, float64].

  • TypeError – If type of align_corners is not bool.

  • ValueError – If any value of output_size is negative or zero when output_size is not None.

  • ValueError – If any value of scales is negative or zero when scales is not None.

  • ValueError – If shape of x is not 5D.

  • ValueError – If none of scales and output_size is specified or both specified.

  • ValueError – If size of scales is not equal 3 when scales is specified.

  • ValueError – If size of output_size is not equal 3 when output_size is specified.

Supported Platforms:

Ascend GPU CPU

Examples

>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> net = ops.UpsampleTrilinear3D()
>>> in_x = Tensor(input_data=np.random.randn(2, 3, 4, 512, 256))
>>> output_size=[4, 64, 48]
>>> out = net(in_x, output_size, None)
>>> print(out.shape)
(2, 3, 4, 64, 48)
>>>
>>> net = ops.UpsampleTrilinear3D()
>>> in_x = Tensor(np.arange(1, 5, dtype=np.float32).reshape((1, 1, 1, 2, 2)))
>>> output_size=[2, 4, 4]
>>> out = net(in_x, output_size, None)
>>> print(out)
[[[[[1.   1.25 1.75 2.  ]
    [1.5  1.75 2.25 2.5 ]
    [2.5  2.75 3.25 3.5 ]
    [3.   3.25 3.75 4.  ]]
   [[1.   1.25 1.75 2.  ]
    [1.5  1.75 2.25 2.5 ]
    [2.5  2.75 3.25 3.5 ]
    [3.   3.25 3.75 4.  ]]]]]