Can you share your config with Mask R-CNN？ I can't reproduce the result on mask_rcnn

liruilong940607 / Pose2Seg

Code for the paper "Pose2Seg: Detection Free Human Instance Segmentation" @ CVPR2019.

http://www.liruilong.cn/projects/pose2seg/index.html

MIT License

532 stars 136 forks source link

Can you share your config with Mask R-CNN？ I can't reproduce the result on mask_rcnn #16

Open sanshibayuan opened 5 years ago

sanshibayuan commented 5 years ago

In the paper you said you "use the author’s released code and configurations from [11]" which is Detecton. I am current training the same dataset on maskrcnn-benchmark, but I cannot get anywhere near the result in your paper (0.532 | 0.433 | 0.648)

I was wondering whether you can share some lights on me, that would be so great!

By the way, I've visualized your results on coco and it's amazing. Great work you guys have done !

sanshibayuan commented 5 years ago

I wonder if you use GT bboxes or not because you did not mention your AP on boxes in the paper. I followed your config in the paper and I can now get (0.429 | 0.325 | 0.554). I don't see where I can improve, can you help me ?