ConstantPad2D

class paddle.nn. ConstantPad2D ( padding: Tensor | Sequence[int] | int, value: float, data_format: DataLayout2D = 'NCHW', name: str | None = None ) [source]

This interface is used to construct a callable object of the ConstantPad2D class. Pads the input tensor boundaries with a constant value.

Parameters

padding (Tensor | Sequence[int] | int) – The padding size. If padding is an int, the same padding is applied to all four sides (left, right, top, bottom). If padding is a list or tuple of four ints, it is interpreted as (pad_left, pad_right, pad_top, pad_bottom).
value (float) – The value to fill the padded areas.
data_format (str, optional) – An string from: 'NCHW', 'NHWC'. Specify the data format of the input data. Default: 'NCHW'.
name (str|None, optional) – For details, please refer to api_guide_Name. Generally, no setting is required. Default: None.

Shape:

x(Tensor): The input tensor of constantpad2d operator, which is a 4-D tensor. The data type can be float32, float64.
output(Tensor): The output tensor of constantpad2d operator, which is a 4-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

>>> input_shape = (1, 1, 2, 3)
>>> pad = [1, 0, 1, 2]
>>> data = paddle.arange(paddle.prod(paddle.to_tensor(input_shape)), dtype="float32").reshape(input_shape) + 1
>>> my_pad = nn.ConstantPad2D(padding=pad, value=0.5)
>>> result = my_pad(data)
>>> print(result)
Tensor(shape=[1, 1, 5, 4], dtype=float32, place=Place(cpu), stop_gradient=True,
[[[[0.5, 0.5, 0.5, 0.5],
   [0.5, 1. , 2. , 3. ],
   [0.5, 4. , 5. , 6. ],
   [0.5, 0.5, 0.5, 0.5],
   [0.5, 0.5, 0.5, 0.5]]]])

          