peternara

Thanks for sharing your code. @zeludeng 1. I am also reproducing with your code (all stages..). However, it is far below the performance of your paper. (About 5-10% of all...

Ooh I didn't read carefully. thank you. @IQ17 I will try it. However, I can't understand why it can't be reproduced with this published code. In the last stage training,...

@gjy3035 i have same problem. you solve it?

넵 감사합니다. 빠른시일내 고대하고 있겠습니다. :)

혹시 언제쯤 될지 알수 있을까요? @jeonsworld

I too have the same problem. > me too > https://github.com/feymanpriv/DOLG/issues/9#issuecomment-1315157627 If I use the DOLG source as is, it will work.!! However, if everything is the same, bacbone (resnet101)...

Hi. Thanks for posting good code. @feymanpriv I am aware of the above issue. I am writing paper. I'm trying to cite your paper. I would like to hear your...

@MhLiao first training is 0.8 and second training(finetuning) is 0.2