Open angus27rzz opened 6 days ago
At a quick glance, this should work for training, though I wonder if the lossless entropy coder also needs adjustment.
A simpler method might be to just rescale the outputs by the desired bin width instead. Since both are uniform quantizers, it should be equivalent.
Feature
Support for Custom Bin Width in
EntropyBottleneck
Motivation
So far only bin width equal to 1 is considered, but would be good to have this as tunable option.
Additional context
Are the only methods that should be changed
quantize
and_likelihood
? Or are there other important changes I am missing.. I'm not sure about_get_medians
.Here is how I would change
quantize
:and here
_likelihood
:Your further guidance is appreciated! Thank you!