search

NVlabs / DG-Net

:couple: Joint Discriminative and Generative Learning for Person Re-identification. CVPR'19 (Oral) :couple:
https://www.zdzheng.xyz/publication/Joint-di2019
Other
1.27k stars 230 forks source link

How is it made sure that the image returned from train_loader_a and train_loader_b is of different identity? #42

Closed chaitrasj closed 4 years ago

chaitrasj commented 4 years ago

Hello, Thank you for this so modular, easy to understand code. I have a doubt, as far as i can understand, you are trying to sample images using train_loader_a and train_loader_b, such that images_a and pos_a are of same id, similarly images_b and pos_b are of same id, but images_a and images_b are different id.. Am i correct? If this is the case, where has the constraint been put that these 2 loaders at run time must load images of different identity? Also there is a method _get_neg_sample in class ReIDFolder. I thought that would be getting used somehow, but I cannot see anywhere that method getting used. Please help me if i am going wrong anywhere. Your reply would be highly appreciated.

Thanks, Chaitra

layumi commented 4 years ago

Hi @chaitrasj Yes. You are right. I did not write this part. However, it does not affect the final result, since it is low probability to have two dataloaders return images of the same identity.