legolas123

Hi, I cannot see where the regularization losses have been added to the data loss. Am I missing something?

Results on caltech-256 dataset

1

https://github.com/khalooei/ALOCC-CVPR2018 is along the same lines of your paper. In that paper, authors have reported state of the art results on caltech-256 dataset. But I failed to reproduce their results....

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...

Pretrained models on Imagenet

1

I did find pretrained models of imagenet dataset with a normal vanilla implementation(https://github.com/shicai/DenseNet-Caffe) for densenet. But since you have changed the names of layer(now a denseblock layer), that pretrained wont...