Res2Net / Res2Net-PretrainedModels

(ImageNet pretrained models) The official pytorch implemention of the TPAMI paper "Res2Net: A New Multi-scale Backbone Architecture"
https://mmcheng.net/res2net/
1.07k stars 215 forks source link

Top-1 and Top-5 Accuracy #20

Closed Zzlongjuanfeng closed 4 years ago

Zzlongjuanfeng commented 4 years ago

Hi, Thanks for releasing pretrained models. I am trying to reproduce the result of Res2Net (top-1 and top-5 accuracy). I am using the official PyTorch training code.

  1. Is the reported result evaluated on the validation set? or test set?
  2. If the result is evaluated on the test set, where could I submit my results? Thank you!
gasvn commented 4 years ago

The model is evaluated on the valiedation set. And we will release a improved version of Res2Net within the next few weeks. It has more than 2% improvement on ImageNet top-1 acc. (Without using se block and other extra blocks.)

Zzlongjuanfeng commented 4 years ago

Thanks for your quick reply. Looking forward to that.