williacode issues

Repositories
Issues
Comments

Results 1 issues of


                                            williacode

Why compute the likelihood contributed by different scales in this way?

I have two questions about the likelihood part. Question 1: In graph.py, https://github.com/boschresearch/hierarchical_anomaly_detection/blob/ca2f1d84615c2ef140a74f4e1515352abff9e938/invglow/invertible/graph.py#L222 the logdet is divided by n_parts (usually 2). Why the logdet is divided by 2 at SelectNode?...