iboing / CliqueNet

Convolutional Neural Networks with Alternately Updated Clique (to appear in CVPR 2018)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Maybe something wrong in ‘/imagenet_pytorch/utils.py’?

tinyRattar opened this issue · comments

I noticed that:

in file ‘/imagenet_pytorch/utils.py’
line 152
block_feature_II = torch.cat((block_feature_II, self.blob_dict_list[1][str(layer_id)]), 1)

maybe the self.blob_dict_list[1] should be replaced with self.blob_dict_list[self.loop_num]
to get the final loop result instead of the first loop result?

Hi,

You are right. When we debuged our code, we always set loop_num = 1. It does not matter. We have rewritten it. Thanks!

Thank you for your notice!
I checked the code again,
but it might be self.loop_num not self.layer_num?

sorry, error has been fixed.