EricGuo5513
commented
1 year ago Hi,
- this range of error should also be fine in my sense. You could try to visualize the results and see if it is correct or not. I know some people have made it smaller. It can be attributed to different environments and hardware platforms.
- The new_joint_vecs are 263-D extracted motion features. The descriptions are as follows:
root_rot_velocity (B, seq_len, 1)
root_linear_velocity (B, seq_len, 2)# root_y (B, seq_len, 1)
ric_data (B, seq_len, (joint_num - 1)3)# rot_data (B, seq_len, (joint_num - 1)6)# local_velocity (B, seq_len, joint_num*3)# foot contact (B, seq_len, 4)
NLP @.***> 于2023年6月26日周一 06:15写道：
1.
When I finished creating the data In the abs(reference1 - reference1_1).sum() part of motion representation.ipynb, I got a value of 1.1061554 instead of a zero. If I don't get a zero, I wonder if I didn't create the data correctly. 2.
I don't know what the new_joint_vecs data means. I would appreciate some clarification please.
— Reply to this email directly, view it on GitHub https://github.com/EricGuo5513/HumanML3D/issues/67, or unsubscribe https://github.com/notifications/unsubscribe-auth/AKRYNBYDLJYN4I6RTPBTSZTXNF4PNANCNFSM6AAAAAAZUCLYKE . You are receiving this because you are subscribed to this thread.Message ID: @.***>
laugher07
When I finished creating the data In the abs(reference1 - reference1_1).sum() part of motion representation.ipynb, I got a value of 1.1061554 instead of a zero. If I don't get a zero, I wonder if I didn't create the data correctly.
I don't know what the new_joint_vecs data means. I would appreciate some clarification please.