zimenglan

i did not use this repo, i just add some code of panet to [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark) (w/o GN).

thanks @thangvubk i will try to add GN to FPN and heads.

hi @thangvubk i add GN to FPN and RoI head, but the performance only gets 38.3%. btw, when training, since the gpu memory limits, so each gpu holds 1 image.

hi @thangvubk i set two images per gpu, the performance can get 0.388, which is still a little gap comparing with the paper.

hi @thangvubk i guess the performance that drops a little is due to that i use `2fc` instead of `Xconv1fc`.

hi @liamsun2019 u can see[ this line ](https://github.com/Jeff-sjtu/res-loglikelihood-regression/blob/master/rlepose/utils/presets/simple_transform.py#L133)

hi @farmingyard i just wonder that how do you write the prototxt? do you code to write? if, can you share it? thanks.

+1

@tianzhi0549 thanks a lot.

glad to see the release of code