mindspore.ops.Pad

class mindspore.ops.Pad(paddings)[source]

Pads the input tensor according to the paddings. For example, to pad only the last dimension of the input tensor, then pad has the form (padding_left,padding_right); to pad the last 2 dimensions of the input tensor, then use (padding_left,padding_right, padding_top,padding_bottom); to pad the last 3 dimensions, use (padding_left,padding_right, padding_top,padding_bottom padding_front,padding_back).

\begin{array}{r} \begin{aligned} input_x_shape = (N_{1}, N_{2}, . . ., N_{n}) \\ \begin{aligned} output_shape = ( & N_{1} + p a d d i n g s [0, 0] + p a d d i n g s [0, 1], \\ N_{2} + p a d d i n g s [1, 0] + p a d d i n g s [1, 1], \\ . . ., \\ N_{n} + p a d d i n g s [n - 1, 0] + p a d d i n g s [n - 1, 1]) \end{aligned} \end{aligned} \end{array}

Parameters: paddings (tuple) – The shape of parameter paddings is (N, 2). N is the rank of input data. All elements of paddings are int type. For the input in 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.

Inputs:

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

Outputs:

Tensor, the tensor after padding.

Raises

TypeError – If paddings is not a tuple.
TypeError – If input_x is not a Tensor.
ValueError – If shape of paddings is not $(N, 2)$ .
ValueError – If paddings.size is not equal to 2 * len(input_x).

Supported Platforms:: Ascend GPU CPU

Examples

>>> input_x = Tensor(np.array([[-0.1, 0.3, 3.6], [0.4, 0.5, -3.2]]), mindspore.float32)
>>> pad_op = ops.Pad(((1, 2), (2, 1)))
>>> output = pad_op(input_x)
>>> print(output)
[[ 0.   0.   0.   0.   0.   0. ]
 [ 0.   0.  -0.1  0.3  3.6  0. ]
 [ 0.   0.   0.4  0.5 -3.2  0. ]
 [ 0.   0.   0.   0.   0.   0. ]
 [ 0.   0.   0.   0.   0.   0. ]]