holyhao

Will you share the trained weights on Imagenet ?

Tanks for for the works. So,did you get better results compared to the proposed by AceCoooool , i find that the reproduced results of the work is lowerer than the...

so，does anyone compare the result of this work with the paper？

emm，i just want to make sure if this repo works well。

> @holyhao I have update the code and results in pre-version，I will update results of v2（using learnable fusion） tomorrow Thanks for your work. By the way,do you train the net...

I try lr=1e-4 with backbone resnet18 ,it works fine and converges faster. But when i try larger batchsize like 32,48, it converges slow and gets worse val results. It confused...

Your reply really inspires me and thank you very much.

> _No description provided._ this just a baseline model，can not get competitive results!

@rootkitchao Tanks for your work. By the way, the warm up train config do not need to set anything like train_num_steps？ And the second trainning steps is 4.5M, it is...

@lupotto Hi, thanks for your reply. Recently，I am training a two classes task (object or not). I want to add some images that do not contain any object as the...