Rui Wang
Rui Wang
For now we just run the model and if it hits the limit we half the subbatch size. We are are trying to add that functionality, but with PyTorch's GRAM...
Hi, Thanks for your question. ShapNet has been designed to be an intrinsic explanation model, which means that it explains itself and only itself by design. However, you _could_ learn...
Hi! Thanks for your interests! 1. The training of this model has nothing different compared to those of other models, you could just replace the model from any other usual...
Hi, Thanks for your interest! Update the code by `git clone` and try with smaller `--subbatch_size`, the default is the number of residues in the sequence.
Hi, Thanks so much for your understanding! And yes we are seeing the same issue that you found and it turned out to be more complicated than we thought. Guess...
Hi! Thanks for your interests! The support for Apple Silicons has been on beta/prototype from PyTorch, which may have created some issues with our code. We have been looking for...
Hi, Yes and we are planning on introducing those. For now you could hack the code yourself. We are planning on this functionality next week. Best, Rui
Hi @sokrypton, Thanks for this info, we'll take a look into it. Best
Hi Dr. @sokrypton, Would you care to give us an example input for this pr?
Hi Dr. @sokrypton, We have reproduced your results and agree that it is really peculiar. We are going to take a deeper look into the reason for this. As for...