Menu

Deep learning for NeuroImaging in Python.

Note

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

class surfify.losses.vae.SphericalVAELoss(beta=9, left_mask=None, right_mask=None, use_mse=True)[source]ΒΆ

Spherical VAE Loss.

Init class.

Parameters:

beta : float, default 9

weight of the kl divergence.

left_mask : Tensor (azimuth, elevation), default None

left cortical binary mask.

right_mask : Tensor (azimuth, elevation), default None

right cortical binary mask.

use_mse : bool, default True

optionally uses the log likelihood.

Follow us

© 2025, nidl developers