HumanML3D

HumanML3D copied to clipboard

Question on double-check difference

2

Hi @EricGuo5513 Thank you for providing such a great dataset. I was doing preprocessing and went through the double-check steps you provided. I got the following results and I was...

pjyazdian

Time to execute raw_pose_preprocessing

2

It appears that the time taken to execute raw_pose_preprocessing.py over all the amass data as 3-4 days. Is it expected or am I doing something wrong.

chinnusai25

visualization of rot in 263-vector

13

Hi, I try to visualize the joints rotation representation, since converting from XYZ to joints rotation takes time. And the result seems not right. Here is my script. I have...

Ying156209

HumanAct12 in SMPL / SMPL-H format?

1

Hi, This is a valuable resource so thanks for that! As I am interested in having HumanML3D in SMPL format, is there a version of `HumanAct12` that is in SMPL...

XefPatterson

About the Mean and Std calculation.

2

Hey, I'm curious in why you use the average number rather than the original variance when u calculate the variance of data in following code. Is there any experiment you...

ZeyuLing

Error when running raw_pose_processing.ipynb

1

when using np.load, it will raise error follows AND when i change np.load, using np.loadtxt it will raise another error HOW to solve it?

xwg0508

how is the coordinate frame defined

1

Hi, thank you for your great work. I have a question about the computation of the quaternion of joints, namely, how are the coordinate frames defined for each joint? For...

gautica

运行raw_pose_processing时出现AssertionError

1

Traceback (most recent call last): File "raw_pose_processing .py" line 280, in m data_m = swap_left_right(data) File "raw_pose_processing .py",line 230,in swap_left_right assert len(data.shape) == 3 and data.shape[-1] == 3 AssertionError

kekekou

Closes #41

felixdivo

Questions about Data

4

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...

ChangeNext