Xinglong Sun

Hi guys. Are you able to achieve the same reported accuracy training from scratch using this repo code? Thanks!

Thanks for your response. However, I'm wondering whether you can release the training loss you recorded during your experiment so that I can compare mine with yours. Thanks!

Thank you very much!

I encountered the same issue and spent nearly 3 hours debugging this. For my case, I didn't clear the local cache /usr/local/lib/cmake. Therefore, the CmakeList found two files of the...

+1 Any update on this issue? This feature will be significantly useful for our usecase as well.

Also, I'm wondering how you're achieving 80.0 mAP on VOC12 Val using only VOC12 train as the training dataset? The results were published on your paper. Would you mind sharing...

Hi thanks for your reply! I'm just wondering, with VOC2007 trainval + VOC2012 trainval, you're able to get a 75.4 map on VOC2012 test. With VOC2007 train and VOC2012 train...