You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have implemented the xnornet ++ paper with resnet-18. You can disable alpha, beta, gamma(scale factors for activation) in model file(BinConv2d). Then you can have the xnornet for resnet-18. Btw xnornet++ is improvement over xnornet and my implementation reaches 60% accuracy for 1 bit activation and 1 bit width.
The link is https://github.com/legolas123/cv-tricks.com/tree/master/xnornet_plusplus
The text was updated successfully, but these errors were encountered:
legolas123
changed the title
I have implemented the xnornet ++ paper with resnet-18. You can disable alpha, beta, gamma(scale factors for activation) in model file(BinConv2d). Then you can have the xnornet for resnet-18. Btw xnornet++ is improvement over xnornet and my implementation reaches 60% accuracy for 1 bit activation and 1 bit width.
I have implemented the xnornet ++ paper with resnet-18.
Jul 22, 2020
I have implemented the xnornet ++ paper with resnet-18. You can disable alpha, beta, gamma(scale factors for activation) in model file(BinConv2d). Then you can have the xnornet for resnet-18. Btw xnornet++ is improvement over xnornet and my implementation reaches 60% accuracy for 1 bit activation and 1 bit width.
The link is https://github.com/legolas123/cv-tricks.com/tree/master/xnornet_plusplus
Originally posted by @legolas123 in #21 (comment)
The text was updated successfully, but these errors were encountered: