Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

MoSh in TotalCapture preprocessing #41

Open
amaliacontiero opened this issue Nov 27, 2024 · 1 comment
Open

MoSh in TotalCapture preprocessing #41

amaliacontiero opened this issue Nov 27, 2024 · 1 comment

Comments

@amaliacontiero
Copy link

amaliacontiero commented Nov 27, 2024

Greetings and thank you for your work on Deep Inertial Poser. I've been trying to preprocess the raw TotalCapture data using your code read_TC_data.py, however, I can't comprehend what "MOSH_BASE_PATH" could be from? I have referred to any relevant MoSh datasets (official site/AMASS) but so far I haven't been able to find a lead. What data is it referring to?
Are the following lines essential to preprocessing?
mosh_path = os.path.join(MOSH_BASE_PATH, name_splits[0], name_splits[1]) mosh_gt = pkl.load(open(mosh_path))['poses'] mosh_ori_0 = pose2matrix(mosh_gt[0])

Thank you in advance!

@amaliacontiero
Copy link
Author

Additional information: I use the following paths,

folder_path = dip18\data_synthesis\TotalCapture_Original (data from original TC dataset)
res_path = dip18\data_synthesis\res\ (I suppose this is the save folder)

MOSH_BASE_PATH = dip18\data_synthesis\MPI_mosh (AMASS data as mentioned in paper, I used SMPL+H)

Traceback (most recent call last):
File "read_TC_data.py", line 271, in
process_imu(all_imu_files[0])
File "read_TC_data.py", line 186, in process_imu
mosh_gt = pkl.load(open(mosh_path))['poses']
FileNotFoundError: [Errno 2] No such file or directory: 'D:\CodeStuff\TIP_Retrain\dip18\data_synthesis\MPI_mosh\s1\acting1.pkl'

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant