microsoft/FocalNet

Issue reproducing evaluation metric for FocalNet+DINO+O365pretrain

RockeyCoss opened this issue · 2 comments

RockeyCoss commented

Thank you for your great work!
However, I am having difficulty reproducing the evaluation metric for the model open-sourced in link. Specifically, my evaluation results is 0.3 AP lower than that you reported in the README.
图片
My command used to run the evaluation is:

python -m torch.distributed.launch --nproc_per_node=4 main.py \
  --output_dir output/path \
	-c config/DINO/DINO_5scale_focalnet_large_fl4.py --coco_path coco/path  \
	--eval --resume checkpoint/path

Could you please help me with this issue? I would be grateful if you could provide some guidance on what I might be doing wrong, or if you could share any additional details about the exact process that you used to compute the evaluation metric.
Thank you very much!

jwyang commented

Hi, @RockeyCoss , thanks for your interest!

I think you are using the default 800x1333 image resolution for your evaluation. Can you change your base in DINO_5scale_focalnet_large_fl4.py with https://github.com/FocalNet/FocalNet-DINO/blob/main/config/DINO/coco_transformer_hres.py?

songyuc commented

Hi, @jwyang, would you consider merging FocalNet/FocalNet-DINO into this repo?