michaelhuang74

@ThienAnh No, I don't have the code for PyCaffe.

@xhsoldier Hi, is it possible to share the trained ckpt file? Thanks.

@chrisckri Thanks for the reply. What I ultimately need is more accurate segmentation. I noticed that the masks produced by the pretrained model are all 21x21. I am not sure...

@DmitryUlyanov Thanks for the response! Could you provide more details? When you say "try eval for instance norm", what do you exactly mean? Many thanks.

@DmitryUlyanov Thanks a lot for the quick response. I will give it a try.

@DmitryUlyanov I added self.bn:evaluate() to Line 48 in the InstanceNormalization.lua file. Then I used the following image as the style image.  Followings are the parameters for training: -style_size 600...

Hi Dmitry, When are you able to post the code of diversity part? Thanks.

Dmitry, thank you very much for sharing the code of the diversity part!!!

@Vladkryvoruchko Thanks for your response. I asked this question because it is allowed to specify the individual weights of different style layers in the similar "fast-neural-style" project by Justin Johnson....

@DmitryUlyanov Thanks for the response. I just asked this question for curiosity. Sometimes, I found that it was difficult to get good results by simply excluding some layers. So I...