Regarding sampling code for visualisation of images

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

Regarding sampling code for visualisation of images #35

Open asthaverma13 opened 4 years ago

asthaverma13 commented 4 years ago

Why you have sampled the images like this?

x_a, x_a_recon, x_aba, x_ab1, x_b, x_b_recon, x_bab, x_ba1

when the fake image wrt x_a is x_ba1, why you are showing x_ab1 with x_a?

layumi commented 4 years ago

Hi @asthaverma13 Thank you. I want to check whether the generated image has correct appearance transform. Therefore, when inference, I provide more samples in one image.

asthaverma13 commented 4 years ago

Hi, Thanks for your reply.

I understand you have provided more samples in one image.

But why x_ab is shown in the set of x_a?

Whereas x_ba is the fake image with respect to x_a.

I hope you get my question. Waiting for your reply