Padding

cupy.pad(array, pad_width, mode, **keywords)[source]

Returns padded array. You can specify the padded widths and values.

This function currently supports only mode=constant .

Parameters:
  • array (array-like) – Input array of rank N.
  • pad_width (int or array-like) – Number of values padded to the edges of each axis. ((before_1, after_1), ... (before_N, after_N)) uniquely pad widths for each axis. ((before, after),) yields same before and after pad for each axis. (pad,) or int is a shortcut for before = after = pad width for all axes. You cannot specify cupy.ndarray .
  • mode (str) –
    ‘constant’
    Pads with a constant values.
  • constant_values (int or array-like) – Used in constant. The values are padded for each axis. ((before_1, after_1), ... (before_N, after_N)) uniquely pad constants for each axis. ((before, after),) yields same before and after constants for each axis. (constant,) or int is a shortcut for before = after = constant for all axes. Default is 0. You cannot specify cupy.ndarray .
Returns:

Padded array of rank equal to array with shape increased according to pad_width .

Return type:

cupy.ndarray

See also

numpy.pad()