mindspore.ops.MirrorPad

class mindspore.ops.MirrorPad(mode='REFLECT')[source]

Pads the input tensor according to the paddings and mode.

Parameters

mode (str) – Specifies the padding mode. The optional values are “REFLECT” and “SYMMETRIC”. Default: “REFLECT”.

Inputs:

  • input_x (Tensor) - Tensor of shape \((N, *)\), where \(*\) means, any number of additional dimensions.

  • paddings (Tensor) - The paddings tensor. The value of paddings is a matrix(list), and its shape is (N, 2). N is the rank of input data. All elements of paddings are int type. For the input in the D th dimension, paddings[D, 0] indicates how many sizes to be extended ahead of the input tensor in the D th dimension, and paddings[D, 1] indicates how many sizes to be extended behind the input tensor in the D th dimension.

Outputs:

Tensor, the tensor after padding.

  • If mode is “REFLECT”, it uses a way of symmetrical copying through the axis of symmetry to fill in. If the input_x is [[1,2,3], [4,5,6], [7,8,9]] and paddings is [[1,1], [2,2]], then the Outputs is [[6,5,4,5,6,5,4], [3,2,1,2,3,2,1], [6,5,4,5,6,5,4], [9,8,7,8,9,8,7], [6,5,4,5,6,5,4]].

  • If mode is “SYMMETRIC”, the filling method is similar to the “REFLECT”. It is also copied according to the symmetry axis, except that it includes the symmetry axis. If the input_x is [[1,2,3], [4,5,6], [7,8,9]] and paddings is [[1,1], [2,2]], then the Outputs is [[2,1,1,2,3,3,2], [2,1,1,2,3,3,2], [5,4,4,5,6,6,5], [8,7,7,8,9,9,8], [8,7,7,8,9,9,8]].

Raises

  • TypeError – If input_x or paddings is not a Tensor.

  • TypeError – If mode is not a str.

  • ValueError – If paddings.size is not equal to 2 * len(input_x).

Supported Platforms:

Ascend GPU CPU

Examples

>>> # case1: mode="REFLECT"
>>> class Net(nn.Cell):
...    def __init__(self, mode):
...        super(Net, self).__init__()
...        self.pad = ops.MirrorPad(mode=mode)
...        self.paddings = Tensor([[1, 1], [2, 2]])
...    def construct(self, input_x):
...        return self.pad(input_x, self.paddings)
...
>>> input_x = Tensor([[1,2,3], [4,5,6], [7,8,9]])
>>> pad = Net("REFLECT")
>>> output = pad(input_x)
>>> print(output)
[[6 5 4 5 6 5 4]
 [3 2 1 2 3 2 1]
 [6 5 4 5 6 5 4]
 [9 8 7 8 9 8 7]
 [6 5 4 5 6 5 4]]
>>> # case2: mode="SYMMETRIC"
>>> pad = Net("SYMMETRIC")
>>> output = pad(input_x)
>>> print(output)
[[2 1 1 2 3 3 2]
 [2 1 1 2 3 3 2]
 [5 4 4 5 6 6 5]
 [8 7 7 8 9 9 8]
 [8 7 7 8 9 9 8]]