egiunchiglia / c-hmcnn Goto Github PK

train.py
The result of 228 line and 231 line are same?
Why not use 228 line result as the output directly？

Hi,

I ran the code on cellcycle_FUN with seed 0 and get an AUPRC of 0.17 max, which was much smaller than the value in your paper.
I tried the code in python 3 and pytorch 1.6 and the code worked just fine, although there's some deprecated warnings.
I am wandering why there is such a difference? Maybe the version difference ?

Thanks for your work!
For the output of get_constr_out to be correct, should not we take the transpose of the constraint matrix? The constrain matrix contains the ancestors at the last dimension, however, we want an ancestor to take the maximum of its descendants.

Hello, I recently study multi-label classification, the fig 1 in the paper may help me analyse my classifier performance. However, I don't know how to draw such a beautiful graph, would you share the graph code with me, I'll greatly appreciate it.