why change mask before output computation?
joemathai opened this issue · comments
Joe Mathai commented
hi,
Thanks for the implementation. I want to know why you have decided to do this
http://masc.cs.gmu.edu/wiki/partialconv
Naoto Inoue commented
Thank you for visiting this repository!
This is to assign pseudo value where output_mask == 0
. Actually, the value 1.0
can be any value a
except 0.0. Without that, zero division error will raise at the pixel where mask_sum == 0
in
After that, we replace
a
with 0.0 again to keep correct value in
Joe Mathai commented
Thanks for the clarification.