hustvl/SparseInst

train on cocodataset ( AP is so low )

Wooho-Moon opened this issue · 2 comments

Wooho-Moon commented

Thanks for nice work! recently, I'm trying to train sparsenetInst on coco2017 dataset. but AP is wired. I read a paper and document

AP AP50 AP75 APs APm APl
17.363 30.127 17.499 2.721 15.622 32.711

my command :
CUDA_VISIBLE_DEVICES=0,1 python tools/train_net.py --config-file configs/sparse_inst_cspdarknet53_giam.yaml --num-gpus 2 --dist-url tcp://127.0.0.1:49153

I don't chang any option. What's wrong with me? How should I do?

116022017144 commented

you see the log and check your backbone whether it loaded sucessfully or not!

  • 👍1
  • 😄2
Wooho-Moon commented

you see the log and check your backbone whether it loaded sucessfully or not!
Thansk for reply :) backbone is sucessfully loaded! but, I cannot reproduce this papers' AP. I don't know what I am missing. and It's a another question. I'd like to reduce the resolution to 192 while remain mask's AP. Could you give a favor?? Plese give me some advices for that task!! thanks.