Releasing the pretrained models
Hi, a very great project. However, when I click the link of pretrained models, I found there are many saliency detection results, instead of the pretrained models, no matter baiduyun or google drive. So can you releas your pretrained models? Thank you.
The pretrained model locates at run-*/models/final.pth.
For each link, there is only one pretrained model, does that mean this pretrained model is trained on all 6 datasets rather than one single dataset?
No, all the models w/o joint training are trained on the DUTS-TR dataset only. The details are well described in the experimental section of the paper.
yuzheyyyy @.***> 于2021年5月24日周一 下午5:53写道:
For each link, there is only one pretrained model, does that mean this pretrained model is trained on all 6 datasets rather than one single dataset?
— You are receiving this because you commented. Reply to this email directly, view it on GitHub https://github.com/backseason/PoolNet/issues/72#issuecomment-846927427, or unsubscribe https://github.com/notifications/unsubscribe-auth/ABYO2OFLO4XW6TCCH74CMP3TPIO3PANCNFSM4T3LY7CA .
--
From BackSeason-刘姜江 Major in Computer Science and Technology Nankai University, Tianjin,300350 P.R.China @.*** @.***>