Hello! I have successfully trained the model by following the README although when I run the run_diffusion.py command as suggested, it is unclear how to retrieve the sequence recovery data from the output csv files. I noticed there is a file label_csv.py which seems to be what computes the sequence recovery however this fails to run since the entries for vh_sample, vl_sample, vh_mask, and vl_mask columns are all blank. For reference, I am running with model=gaussian. @ngruver , could you provide guidance as to how to run this correctly?
Hello! I have successfully trained the model by following the README although when I run the
run_diffusion.pycommand as suggested, it is unclear how to retrieve the sequence recovery data from the output csv files. I noticed there is a filelabel_csv.pywhich seems to be what computes the sequence recovery however this fails to run since the entries for vh_sample, vl_sample, vh_mask, and vl_mask columns are all blank. For reference, I am running withmodel=gaussian. @ngruver , could you provide guidance as to how to run this correctly?