training about realtime_multi-person_pose_estimation HOT 3 OPEN

limbSeq = [[2,3], [2,6], [3,4], [4,5], [6,7], [7,8], [2,9], [9,10],
[10,11], [2,12], [12,13], [13,14], [2,1], [1,15], [15,17],
[1,16], [16,18], [3,17], [6,18]]

mapIdx = [[31,32], [39,40], [33,34], [35,36], [41,42], [43,44], [19,20], [21,22],
[23,24], [25,26], [27,28], [29,30], [47,48], [49,50], [53,54], [51,52],
[55,56], [37,38], [45,46]]

Hello, I want to ask, how is the order of this lookup connection defined? I am looking forward to your reply, thank you very much.

from realtime_multi-person_pose_estimation.

@wwxzxd the digits in LimbSeq are order of heatmap mapping to jionts. for example ,[2,3] maybe mean the limb of left upper arm,so [31,32] should mean the PAF of left upper arm index in output of net.forward(),and 31 means X ,32 means Y

from realtime_multi-person_pose_estimation.

@wwxzxd the digits in LimbSeq are order of heatmap mapping to jionts. for example ,[2,3] maybe mean the limb of left upper arm,so [31,32] should mean the PAF of left upper arm index in output of net.forward(),and 31 means X ,32 means Y

Thank you, I probably understand what you mean, but I am curious why this is the order.
limbSeq = [[2,3], [2,6], [3,4], [4,5], [6,7], [7,8], [2,9], [9,10],
[10,11], [2,12], [12,13], [13,14], [2,1], [1,15], [15,17],
[1,16], [16,18], [3,17], [6,18]]

from realtime_multi-person_pose_estimation.