Open krumo opened 2 years ago
i also meet with this problem, have you solved this issue?
I also meet with this problem, you can degrade the detectron2 version to a past version, e.g. 932f25ad38768dc88cc032f3db57ce30d2bea9c1 is okay for me.
I solved this problem. Note that all the keys in the checkpoint have the same name in the model but with a "pixel_decoder" additional. In the file mask2former/modeling/meta_arch/mask_former_head.py comment/erase all the line 33-36 (if "sem_seg_head" in k and not k.startswith(prefix + "predictor"):) this lines add a "pixel_decoder" to the checkpoints keys.
Just return in "_load_from_state_dict" in the file mask2former/modeling/meta_arch/mask_former_head.py works for me.
Hi, I am trying to evaluate the model trained on Cityscapes by running
python train_net.py --config-file configs/cityscapes/panoptic-segmentation/maskformer2_R50_bs16_90k.yaml --eval-only MODEL.WEIGHTS exp/model_final.pth
. However, when I load the model I get the following warning:And the test results look weird. The PQ, SQ, RQ are all 0s. Would you mind sharing some suggestions?