Open Ze-Yang opened 4 months ago
I managed to reproduce other settings, except for 100-5 panoptic segmentation. Any advice is highly appreciated. Thank you.
1-100 | 101-150 | all | |
---|---|---|---|
reported | 34.4 | 15.9 | 28.2 |
reproduced | 30.2 | 20.4 | 27.0 |
Script:
cfg_file=configs/ade20k/panoptic-segmentation/maskformer2_R50_bs16_160k.yaml
base=ade_ps
cont_args="CONT.BASE_CLS 100 CONT.INC_CLS 5 CONT.MODE overlap SEED 42"
task=mya-pan_100-50-ov
name=MxF_nosoft
meth_args="MODEL.MASK_FORMER.TEST.MASK_BG False MODEL.MASK_FORMER.PER_PIXEL False MODEL.MASK_FORMER.SOFTMASK False MODEL.MASK_FORMER.FOCAL True"
## 100-5 ###
comm_args="OUTPUT_DIR ${base} ${meth_args} ${cont_args}"
inc_args="CONT.TASK 1 CONT.WEIGHTS ${base}/${task}/${name}/step0/model_final.pth SOLVER.MAX_ITER 2000 SOLVER.BASE_LR 0.00005"
python train_inc.py --num-gpus 2 --config-file ${cfg_file} ${comm_args} ${inc_args} NAME ${name}_PSEUDO_UKD10Rew CONT.DIST.PSEUDO True CONT.DIST.KD_WEIGHT 10.0 CONT.DIST.UKD True CONT.DIST.KD_REW True
for t in 2 3 4 5 6 7 8 9 10; do
inc_args="CONT.TASK ${t} SOLVER.MAX_ITER 2000 SOLVER.BASE_LR 0.00005"
python train_inc.py --num-gpus 2 --config-file ${cfg_file} ${comm_args} ${inc_args} NAME ${name}_PSEUDO_UKD10Rew CONT.DIST.PSEUDO True CONT.DIST.KD_WEIGHT 10.0 CONT.DIST.UKD True CONT.DIST.KD_REW True
done
Hey! Sorry, I didn't get the notification.
The scripts for training CoMFormer in ADE 100-5 were provided here: scripts/ade5.sh. Have you tried checking the parameters if they match?
CONT.DIST.PSEUDO True CONT.DIST.PSEUDO_TYPE 1 CONT.DIST.KD_WEIGHT 10. CONT.DIST.UKD True CONT.DIST.KD_REW True
Yes, they match. But CONT.DIST.PSEUDO_TYPE 1 is no longer in use in the code.
Ok. Can you also check all the libraries match? (I used the mask2former default ones).
Your code already includes the mask2former library. It's self-contained. I use the one you provided in this repo.
Ok. Then I don't know what it may be. Have you tried again? Maybe it is a large randomness? Actually, it seems you're better in the new classes and worse on the old ones.
I ran the script as shown below. Unfortunately, I can only get PQ 30.28 vs. reported PQ 36.7 for 100-50. Could you please advise if anything wrong with my configs? Thanks.
Modifications:
Issues:
CONT.DIST.PSEUDO_TYPE=2
?