EvanKomp
EvanKomp
@guillaumeeb I think that is a reasonable strategy, and pretty flexible. If you end up with an extreme case like mine where tasks can take order of magnitude differences in...
@dberenbaum ``` stages: preprocess: cmd: ./prepare.sh outs: - ./data/preprocessing/ predict: cmd ./predict.sh params: - model_type # One of A, B, C deps: - ./data/preprocessing/ # THIS ONLY NEEDS TO BE...
Affirmative. Thanks for your work. I think expanding on the yaml like you would with a `cache` tag would be best. eg. ``` stages: preprocess: cmd: ./prepare.sh outs: - ./data/preprocessing/...
Same issue. Eval loop at the start of training works, then train for a while, eval again, and then as soon as training resumes after the second eval loop it...
@LTEnjoy I was running a simple regression training! I lost the traceback because I did not copy the notebook. I will try to run it again and see if I...
@LTEnjoy sorry for tardiness, will give it a go maybe next week.
I am observing this too.
Same problem!
@a-r-j It looks like that function also requires keep_hets as a list. Is there no way to keep all hetatms without having to specify the names?
@martin-steinegger Thanks for the reply. The below got me to the point of a search that runs without error: ``` ### convert alignment to msa database foldseek convertmsa fold_align_aa.fa query/query_msa...