jeong-tae

@jackshaw hello, jachshaw I am not sure what you mean. Do you mean normalization? or subtract mean? Whatever you do, it will not effect too much... maybe. But actually it...

Nope. i didn't. In pytorch, there is image resize preprocessing that used in the paper. You can easily find it in the pytorch docs.

i think so too exactly same! i tried with that way but i can’t reproduce the result. i will soon try again.

@Lzc6996 Okay, I will try that and let you know results

does test loss also very less? Focal loss can be very less by compressing a easy classes but it doesn't mean that not working. I am also trying to reproduce...

of course long time ago, I tried. I remember that performance was poor on VOC dataset. I can’t remember exact numbers... hm, it was around 40mAP or 60mAP. haha I...

@EvanAlbee `x = x[:, 1:]` doesn't mean that exclude all negative matches. Negative can be defined "predicted as positives but true labels are background cases" in here. Well, we still...

Anyone have results on this repository? i also wanna know!