Open aifeixingdelv opened 3 weeks ago
xv shows less stable training in base scale.
the difference between xv1a xv2a and xv3a is the way how dts is generated.
in my ablations, v0 v1 v2 shows a little difference. For details you can see the arxiv paper.
xv shows less stable training in base scale.
the difference between xv1a xv2a and xv3a is the way how dts is generated.
in my ablations, v0 v1 v2 shows a little difference. For details you can see the arxiv paper.
Thank you for your rapid reply!
Thank you very much for your contribution. I have some question, really looking forward to your reply