Reproducing MaskCut & CutLER (1 round) on COCO val2017

[conordete]

Hello!

I have recently attempted to reproduce the numbers reported in the paper for COCO val2017, both for MaskCut and Cutler with 1 round of training, but unfortunately, the results I got were not matching what I was expecting from the reported results in the paper.
For MaskCut, I got 1.7 APmask instead of 2.2. I also ran the pseudo mask generation for all of ImageNet and trained a Cascade Mask R-CNN with your config. For 1 round of training on the pseudo masks, I got 7.3 APmask instead of the reported 8.8.

I was wondering if you could help out here to identify potential mistakes I might have made? I was closely following the instructions of the repository, also using the same torch version. I also got a message that all folders were annotated, confirmed your print statement the merge_jsons.py script.

Furthermore, it would be super helpful to have the code used for evaluate the MaskCut pseudo masks. Would it be possible for you to release this script? :)

Many thanks in advance!

[abhi12emails]

@conordete Hey, i have been attempting to run and reproduce the results but ran into some initial setup errors. would you be willing to guide me through? P.S I'm new to cloning models from github.
thanks :)