cupyx.scipy.ndimage.gaussian_filter#

cupyx.scipy.ndimage.gaussian_filter(input, sigma, order=0, output=None, mode='reflect', cval=0.0, truncate=4.0, radius=None, axes=None)[source]#

Multi-dimensional Gaussian filter.

Parameters:

input (cupy.ndarray) – The input array.
sigma (scalar or sequence of scalar) – Standard deviations for each axis of Gaussian kernel. A single value applies to all axes.
order (int or sequence of scalar) – An order of 0, the default, corresponds to convolution with a Gaussian kernel. A positive order corresponds to convolution with that derivative of a Gaussian. A single value applies to all axes.
output (cupy.ndarray, dtype or None) – The array in which to place the output. Default is is same dtype as the input.
mode (str or sequence of str) – The array borders are handled according to the given mode ('reflect', 'constant', 'nearest', 'mirror', 'wrap'). Default is 'reflect'. By passing a sequence of modes with length equal to the number of axes along which the input array is being filtered, different modes can be specified along each axis. For more details on the supported modes, see scipy.ndimage.gaussian_filter().
cval (scalar) – Value to fill past edges of input if mode is 'constant'. Default is 0.0.
truncate (float) – Truncate the filter at this many standard deviations. Default is 4.0.
radius (int, sequence of int, or None) – Radius of the Gaussian kernel. The radius are given for each axis as a sequence, or as a single number, in which case it is equal for all axes. If specified, the size of the kernel along each axis will be 2*radius + 1, and truncate is ignored. Default is None.
axes (tuple of int or None) – If None, input is filtered along all axes. Otherwise, input is filtered along the specified axes. When axes is specified, any tuples used for sigma, order, mode and/or radius must match the length of axes. The ith entry in any of these tuples corresponds to the ith entry in axes. Default is None.

Returns:

The result of the filtering.

Return type:

cupy.ndarray