can release the high AP model, e.g. HRNet + RLE (Ours) HRNet-W48 (75.7)?

[zimenglan-sysu-512]

[Eatzhy]

读完摘要想法很不错，摘要里这句We show its potential in various human pose estimation tasks with comprehensive experiments.Compared to the conventional regression paradigm, regression with RLE bring 12.4 mAP improvement on MSCOCO without any test-time overhead。实验对比很有意思，值得思考。但是用起来训练不好优化，不如MSE来的直接，权重有的也没给，其他的实验map提升不明显，后面看看mmpose整合后怎么样。