eliphatfs / SkeletonMerger

Code repository for paper `Skeleton Merger: an Unsupervised Aligned Keypoint Detector`.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Want a pretrained model

YYYYYHC opened this issue · comments

I trained your model locally with default settings, however, the result is not as good as shown in the paper. I write this issue to ask for your help. Could you please provide me with your training settings( epoch, batch num, optimizer). Also, I would be very glad to get a pretrained model from you. Best wishes! 😄

commented

I did not keep the specific model checkpoint used for paper evaluations, but here is a trained model for the chair category. It achieves almost the same DAS (76.74 locally) as claimed in paper and also on-par IoU (65.83 locally, still SOTA level). It is trained with default parameters except that the device is set to a GPU.
merger.zip