fast-neural-style icon indicating copy to clipboard operation
fast-neural-style copied to clipboard
verified publisher icon jcjohnson

a question about StyleLoss.lua

Open MarkOUzx opened this issue 8 years ago • 0 comments

The initializing function function StyleLoss:__init(strength, loss_type, agg_type) have an option loss_type, but I found that in the train.lua, you didn't give an input parameter. Does it mean the default option, "L2", appearing in the StyleLoss.lua, is the best choise for training?

MarkOUzx avatar Apr 21 '18 11:04 MarkOUzx