Raph
Results
4
issues of
Raph
Im using my own processed npz files to test Deciwatch , but why the output error is bigger than input error?
is it refer to Exploiting Spatial-temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks, the refinement module? how many epochs do I need to train to add this module？
What is the purpose of confidence in the code, Can adding this dimension additionally improve accuracy? Will this bring additional computational burden?