search

LongLong-Jing / Cross-Modal-Center-Loss

Cross-Modal Center Loss for 3D Cross-Modal Retrieval (CVPR2021)
33 stars 9 forks source link

self.k = args.k #1

Open HelloMaroon opened 3 years ago

HelloMaroon commented 3 years ago

It seems like that there's no argument like k, emb_dims in args, which will be used in class DGCNN(nn. Module). Then it leads to the mistake: AttributeError: 'Namespace' object has no attribute 'k'

piseabhijeet commented 3 years ago

Hi @HelloMaroon , @LongLong-Jing

I tried to use the default parameters from the function and the paper and tried but still didn't work. Did you get it to work?

Any help would be appreciated :)

duzhenjiang113 commented 3 years ago

It seems like that there's no argument like k, emb_dims in args, which will be used in class DGCNN(nn. Module). Then it leads to the mistake: AttributeError: 'Namespace' object has no attribute 'k'

have you solved the issue? i have the same problem

piseabhijeet commented 3 years ago

It seems like that there's no argument like k, emb_dims in args, which will be used in class DGCNN(nn. Module). Then it leads to the mistake: AttributeError: 'Namespace' object has no attribute 'k'

have you solved the issue? i have the same problem

Yes, use k=20 and emb_dims=512. It should work.

HelloMaroon commented 3 years ago

https://github.com/WangYueFt/dgcnn/blob/master/pytorch/main.py Hey guys, maybe you can find some useful messages on this website. I guess the author may reference this code.

HelloMaroon commented 3 years ago

However, there're other problems I haven't solved so I turned to other codes now.