ReflectionPad3D

class paddle.nn. ReflectionPad3D ( padding: Tensor | Sequence[int] | int, data_format: DataLayout3D = 'NCDHW', name: str | None = None ) [source]

This interface is used to construct a callable object of the ReflectionPad3D class. Pads the input tensor boundaries using reflection of the input boundaries.

Parameters

padding (Tensor | Sequence[int] | int) – The padding size. If padding is an int, the same padding is applied to all six sides (left, right, top, bottom, front, back). If padding is a list or tuple of six ints, it is interpreted as (pad_left, pad_right, pad_top, pad_bottom, pad_front, pad_back). Padding width must be less than the corresponding input dimension.
data_format (str|None) – An string from: “NCDHW”, “NDHWC”. Specify the data format of the input data. Default: "NCDHW"
name (str|None, optional) – The default value is None. Normally there is no need for user to set this property. For more information, please refer to api_guide_Name.

Shape:

x(Tensor): The input tensor of reflectionpad3d operator, which is a 5-D tensor. The data type can be float32, float64.
output(Tensor): The output tensor of reflectionpad3d operator, which is a 5-D tensor. The data type is same as input x.

Returns: The padded tensor.
Return type: Tensor

Examples

           >>> import paddle
>>> import paddle.nn as nn
>>> # from reflection_padding_layers import ReflectionPad3D

>>> input_shape = (1, 1, 1, 2, 3)
>>> pad = [1, 0, 1, 0, 0, 0]
>>> data = paddle.arange(paddle.prod(paddle.to_tensor(input_shape)), dtype="float32").reshape(input_shape) + 1
>>> # data = [[[[[1., 2., 3.], [4., 5., 6.]]]]]
>>> my_pad = nn.ReflectionPad3D(padding=pad)
>>> result = my_pad(data)
>>> print(result)
Tensor(shape=[1, 1, 1, 3, 4], dtype=float32, place=Place(cpu), stop_gradient=True,
[[[[[5., 4., 5., 6.],
    [2., 1., 2., 3.],
    [5., 4., 5., 6.]]]]])

          