Deep learning for NeuroImaging in Python.

Note

This page is a reference documentation. It only explains the function signature, and not how to use it. Please refer to the gallery for the big picture.

surfify.nn.functional.circular_pad(x, pad)[source]¶

Circular pad of a tensor.

Since a spherical patterns are circularly continuous with respect to the azimuth, we need to apply circular padding to the boundaries of azimuth for the flattened 2-D map but applied zero padding to the boundaries of evaluation.

Parameters:

x : Tensor (samples, channels, azimuth, elevation)

input tensor.

pad : int or tuple (pad_azimuth, pad_elevation)

the size of the padding.