search

dswah / sgcrfpy

SGCRFpy: Sparse Gaussian Conditional Random Fields in Python
MIT License
29 stars 5 forks source link

infinite loss #12

Open dswah opened 8 years ago

dswah commented 8 years ago

make sure we are not penalizing the diagonals as recommended by S Kim in SNP eQTL paper.

also, why is our loss undefined so often?

dswah commented 8 years ago

made change to diagonals...

havent run across the undefined loss problem again, yet...

dswah commented 8 years ago

inf loss is happening when we use very large matrices. in this case the determinant is overflowing!

use np.linalg.slogdet