Closed junliang230 closed 4 years ago
In addition to the structure change as you mentioned, we have also improved the training strategy.
thanks,will the training strategy be released? (If not convenient, feel free to close this issue)
It will be released. But for now, we are still working on improving the training strategy.
ok, I am looking forward it
thank your amazing work. compared with original version of Res2Net, res2net_v1b make two difference: 1.replace conv 7*7 with this 2.downsample replace conv(stride=2) with avgpool2d this
after changing these, Res2Net_v1b has more than 2% improvement on ImageNet top1 acc. compared with original version of Res2Net am I right? thank your reply