3 Commits

Author	SHA1	Message	Date
Jacob Silterra	9d0bf3d884	Set any nans/infs in model scores to a small value. ... With some low (but non-trivial) frequency, processing through the convolutional layers diverge and node attributes become a mixture of nan and inf (which seem to all turn to nan). This later throws an exception during the Kabsch transform, which ruins results for the whole complex. Setting these to 0 basically skips an iteration, at worst it ruins one of the sampled complexes, but leaves the others. Note this is only applied to the main model, *not* the confidence model.	2024-06-10 12:44:45 -04:00
Gabriele Corso	001c4fa46e	first commit v1.1	2024-02-28 11:21:46 -05:00
Gabriele Corso	ac5612da4f	first commit	2022-10-04 20:11:55 -04:00