Kevin Chen Zihao

@LimBee @wuguangbin1230 @lxtGH @XuSen123 @FoolishMao what the performance did you get?

I have a relevant question. I'm not sure what's the difference between .pth and .pkl weights and what exactly they are used for? when I try to run inference with...

@joshualmitchell Thank you for replying. I feel the same. Do you know if there is the difference between --load_detectron and --load_ckpt?

@lsrock1 Thank you for your kind and detailed explanation. That helps a lot!

@cxxgtxy Thank you. I will check the repo. Do they offer training scripts by the way?

My observation: he doesn't have the first conv with kernel-7, and the following maxpooling layer. In total it's downsampled by three times 32*32 -> 4*4, while for a normal ResNet...

I use python3.7 with pytorch 1.2.0 and the bug is fixed. cheers

According to the paper right now, I believe they should be both 160 instead. p.s. The paper has fixed the stride error in V3-small

> Rename the folder "roi_align" (in your > decompressed directory) to other name solves the problem. brilliant, this solves the issue. Thank you