Use FUpred to split protein domain

[dh97]

Hi, When I use FUpred to split the protein domain, I meet the following error:
`Compilation is falling back to object mode WITHOUT looplifting enabled because Function "cal_large_matrix1" failed type inference due to: Cannot determine Numba type of <class 'numba.core.dispatcher.LiftedLoop'>`
so, what's wrong, it seems that there are some files missing?

[dh97]

oh, I directly use the example command:
./run-FUpred.pl ./example/6paxa.fasta

[zcx@umich.edu]

This is just a warning from the contact predictor used by FUpred. It uses JIT compiler from numba. Without numba, the program will still run correctly, albeit slower.

[dh97]

thanks, the problem has been solved, since I used pytorch==1.7.0 version, so there is something wrong with loading the model.