Feng Wang
Thanks @zhiqwang for your proposal and @datumbox for inviting me. I would like to contribute a implemenentation of YOLOX to torchvision and I wonder what should I do in order...
@datumbox Sorry for my late reply — I'm on my vacation these days. I check the references you mentioned above and I think implemented a YOLOX model in torchvision is...
> Sorry what do you mean by DDL? I mean, deadline
Hi @datumbox , I haven't faced any blockers here with the implementation. The only bad news for us is that I transferd to a new work group and my new...
It seems a compiling error. You could remove tree-filter code to train boarderDet
Such an issue might be caused by `F.vision.interpolate`, using `scale_factor` instead of `target_size`
Sounds like your resize didn't keep the aspect ratio?
please following what REAME says and the module named dl_lib.configs
Ok, I see what you means. I will fix this later.
Your batchsize is too small in my opinion. You may check your log file and your loss might not converage.