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
1.28k stars 228 forks source link

When I use another dataset，The generated data is not as much as the original data #32

Open CWF-999 opened 4 years ago

CWF-999 commented 4 years ago
  1. When I use another dataset，The generated data is not as much as the original data.For example, my training set is 3G, and I only got 2G generated pictures in the end. What is the reason? Where else to modify?
  2. In addition, if the number of training iterations is increased (the default is 100,000), will the quality of the generated images be higher?

I will be grateful if you can answer

layumi commented 4 years ago

Hi @wfchenwf Sorry for the late response. I think I was working on the IJCAI submission at that time.

  1. How do you generate the samples? Actually, if the original dataset contains N images, you could generate NxN images theoretically.
  2. Actually, it could be improved. But the improvement might be small.