"h36m_part.h5" missed

Hello. Thanks for your excellent job.
I met an error while running your code. It seemed that I missed this file "h36m_part.h5". Where can I get this file?
File "dynaboa.py", line 94, in __init__
fin = h5py.File('/dev/shm/h36m_part.h5', 'r')

Besides, will you offer a demo program to run on videos in the future?

Thanks for your interest. I update the readme and the code just now. You can additionally download this file and Human 3.6M to try our DynaBOA.

I will release the code running on the demo videos soon.

Thank you for the detailed answer!

Thanks for your reply.
I think that the missed file is "h36m_part.h5", but the upper link given is"h36m_random_sample_center_10_10.pt".
Can you share the file "h36m_part.h5" or preprocessed file to change h36m to "h36m_part.h5"? Thanks.

I'd like to share h36m_part.h5. But this file is too large. My google drive doesn't have enough space to share it. By downloading h36m_random_sample_center_10_10.pt and Human 3.6M, you can also run DynaBOA.

In fact, the only difference between the two choices is that we offline crop the images of Human 3.6M and save them into h36m_part.h5.

Thanks a lot for your prompt reply!

DynaBOA/boa_dataset/pw3d.py

Line 34 in 368a10a

self.pw3d_datas = glob.glob('data/dataset_extras/3dpw_[0-9]*_[0-9].npz')

If data is used, this path should be changed to self.pw3d_datas = glob.glob('data/data_extras/3dpw_[0-9]*_[0-9].npz').

DynaBOA/config.py

Line 7 in 368a10a

PW3D_ROOT = '/data/syguan/human_datasets/3dpw'

And this line should be noticed to change according to your own 3dpw path.

Besides, data seem to lose directory spin_data spin_data.

And could you share the preprocess file to change raw h36m videos to the images? Thanks.

Thanks for your detailed comments! To process Human 3.6M, you can refer to this script.

Thanks for your patient reply :)

I update my repo with more detailed instructions to process Human 3.6M. @MooreManor

Thanks! I'll take a try.