Caffe-DeepBinaryCode icon indicating copy to clipboard operation
Caffe-DeepBinaryCode copied to clipboard

Published 20 hours ago • verified publisher icon kevinlin311tw

the weight of loss function

Open yeqq123 opened this issue 7 years ago • 3 comments

Hi, kevin I understand the weight of classification error is in your paper(formula (2)) and the weight of binarization similarity in your paper(formula (7)) is different. So I can't understand what the W stand for in your paper(formula (8)) thx.

yeqq123 avatar Jan 24 '18 05:01 yeqq123

W is the network parameters. BTW, this repo does not support multi-label version.

kevinlin311tw avatar Jan 24 '18 07:01 kevinlin311tw

And I can't find the file which contain the loss function, can you indicate the file's name? Thx.

yeqq123 avatar Jan 24 '18 13:01 yeqq123

Have you found the loss function

ximi2018 avatar Mar 07 '20 11:03 ximi2018