Michael Plainer

I don't think that we will add support for this. But the easiest way for you is to add one of these lines in the script https://github.com/GioBonvi/GoogleContactsEventsNotifier/blob/7e657a9e606f449fef22feae68d448d11083122b/code.gs#L2440-L2444 For example you...

That is a great find. Please keep us in the loop!

That is unfortunate. I was checking it on my (working) configuration and the project status is set to test. Thank you for looking into this!

Thank you for raising this issue. We have not committed this part of the code yet. However, the metrics should be pretty straightforward. If you need any help implementing them,...

We experienced similar behavior when training the model. This is why we optimized rmsd_lt2. You should see this increase. Do you?

It was common for us to have epochs with outliers and very big losses. But values should not be consistently this large. In our run `valinf_rmsds_lt2` only started to be...

Could you try --limit_complexes 100 and setting the train set to validation set? i.e. --split_train data/splits/timesplit_no_lig_overlap_val_aligned --split_val data/splits/timesplit_no_lig_overlap_val_aligned --limit_complexes 100 And see if the problem persists? With this, we can...

You have to comment out this line for it to work https://github.com/plainerman/DiffDock-Pocket/blob/98a15235eeec7561fc9f183823273452270487b8/datasets/pdbbind.py#L988

Maybe related: https://github.com/plainerman/DiffDock-Pocket/issues/6 (which has been fixed). So maybe it is worth to pull again

Sorry for not getting back to you sooner. I don't have any concrete results yet, but I think there might be an issue when I ported parts of our code...