Hao Li

icon indicating a website link lifuguan.github.io icon indicating an email [email protected]

icon company Northwestern Polytechnical University icon location China, Beijing icon location P.h.D candidate at NWPU for deep learning.

Results 4 comments of Hao Li

you can change TP and FN like this. TP = ((SR==1).byte()+(GT==1).byte())==2 .FN = ((SR==0).byte()+(GT==1).byte())==2.

Thanks!

Why is the number of categories for training coco 2 instead of 81?

In pretrain procedure, only *foreground* and *background* is unsed

Why is the number of categories for training coco 2 instead of 81?

Because both freemask and self-sup training are total the same, except for the dataset. The annotations of self-sup cames from the predictions of freemask training. It's general in self-sup training.

The .pkl checkpoints can't be transfered.

Same problem. Wish to be responded.