Sachin Kadyan

Upon investigation, the error is genuine but the cause is different. Obsolete PDB ids were not getting replaced by newer ones, but not just for new additions to obsolete.dat, but...

Hi yuzhiguo07, Sorry, that you are facing this issue. Can you please share some details about how you reproduced this? Namely, what was the specific protein for which the template...

Thanks for letting us know. It seems that because of some reason the obsolete protein id '6ek0' was not replaced by the newer protein id '6qzp' (as seen from obsolete.dat)...

Couple of questions to help figure out this issue: 1. Are you passing the `obsolete.dat` path in the script call? 2. Did you generate the `release_dates` file? (`release_dates` can be...

@hellofinch It seems that your command does not contain the path of the `obsolete.dat` file to the script. Upon inspection, I figured out that this is because (specifically) the training...

@hellofinch Do you see any the alignment files and the predicted structure in your output directory? If the files are there, it means that there was no error during the...

Here is an output of another time we observed this `IllegalMemoryAccess` issue (at epoch 150, so quite early in the epoch). In this case, `CUDA_LAUNCH_BLOCKING` was *not on* so it's...

Hey @ptrblck @ngimel , Is there any update on this issue? Is there anything else I can provide to help understand the root cause of this issue?

I see. The change that you are suggesting I incorporate - that seems to be a fix for getting the stack trace. Do you think in my case, the stack...

Hey @ar-nowaczynski Thanks for the reply and the questions raised. 1. The computational graph is fixed as the every sequence is either cropped or padded to a predefined length. Also,...