Menu

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.losses.vae.log_likelihood(recon, xs)[source]ΒΆ

Computes the log likelihood of the input sample given the reconstructed sample

Parameters:

recon : Tensor (N, C, H, W)

reconstructed images

xs : Tensor (N, C, H, W)

original images

Returns:

log_likelihoods : Tensor (N)

log likelihood for each sample

Follow us

© 2025, nidl developers