SimVP-Simpler-yet-Better-Video-Prediction icon indicating copy to clipboard operation
SimVP-Simpler-yet-Better-Video-Prediction copied to clipboard

Published 20 hours ago • verified publisher icon gaozhangyang

Effect of the input size on the performance of SimVP

Open Hugh-Cai opened this issue 2 years ago • 2 comments

Hi, Gao I find the input size is almost smaller than 128 in the paper. So, I take a training on my own dataset which are same expect for different input size (128, and 512), leading to different performance:

  • for size 128, the performance has improved signigicantly;
  • but for size 512, the performance is always oscillatory during training.

What causes this situation? Can you help me with the questions or give me some suggestions?

Thanks

Hugh-Cai avatar Oct 10 '22 07:10 Hugh-Cai

Thank you for raising a more challenging task. Currently, I don't have a better solution. But it is worth further research.

gaozhangyang avatar Feb 07 '23 06:02 gaozhangyang

I trained on resolution 64 for KTH dataset and have the same problem. The possible reason is that training is difficult if the resolution is too high; If the resolution is too small, it is difficult to extract more details; Perhaps 128 is a more suitable compromise. More research is needed.

image

JunyaoHu avatar Mar 26 '23 03:03 JunyaoHu