DMGNN
DMGNN copied to clipboard
The implementation of DMGNN
Hello, are there some more instructions for the code implementation.
c12_1 = self.j2p_1(x_s1_1, x_s2_1, relrec_s1, relsend_s1, relrec_s2, relsend_s2) r12_1 = self.p2j_1(x_s2_1, x_s1_1, relrec_s2, relsend_s2, relrec_s1, relsend_s1) c23_1 = self.p2b_1(x_s2_1, x_s3_1, relrec_s2, relsend_s2, relrec_s3, relsend_s3) r23_1 = self.b2p_1(x_s3_1, x_s2_1, relrec_s3, relsend_s3,...
Can you tell me how to process the skeleton sequence coordinates of 15 key points in several frames and then train the network for prediction?