SSAH icon indicating copy to clipboard operation
SSAH copied to clipboard

pretrained vgg_f

Open zyfsa opened this issue 6 years ago • 3 comments

hi, your work is great. Although there are some differences with the original paper. can I get your pretrained vgg16.mat?thanks Besides, your tensorflow version is ?

zyfsa avatar Oct 14 '18 01:10 zyfsa

Hi, have you found the right imagenet-vgg-f.mat? I have tried this one--http://www.vlfeat.org/matconvnet/models/imagenet-vgg-f.mat but there is a problem "mean = data['normalization'][0][0][0] KeyError: 'normalization'" Then I tried this http://www.vlfeat.org/matconvnet/models/imagenet-vgg-verydeep-19.mat as https://github.com/anishathalye/neural-style/issues/4 advised. The problem--KeyError: 'normalization-- solved, but there are still erros, as the layers written in code of SSAH are not the same in the imagenet-vgg-verydeep-19.mat

so, I want to know where to get the imagenet-vgg-f.mat used in this paper.

cheer00 avatar Oct 16 '18 10:10 cheer00

hi, your work is great. Although there are some differences with the original paper. can I get your pretrained vgg16.mat?thanks Besides, your tensorflow version is ?

have you got the vgg16.mat?

cheer00 avatar Oct 16 '18 10:10 cheer00

@cheer00 hello, I advise you load the imagenet-vgg-f.mat in matlab, and analyze it. If you also are puzzled,you can my watch my repository (cvpr2108-SSAH). I follow this work and have little modification

zyfsa avatar Oct 16 '18 14:10 zyfsa