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

Missing subdataset "humanact12" when run script raw_pose_processing.ipynb #54

Open
spzhuang opened this issue Apr 24, 2023 · 5 comments · May be fixed by #62
Open

Missing subdataset "humanact12" when run script raw_pose_processing.ipynb #54

spzhuang opened this issue Apr 24, 2023 · 5 comments · May be fixed by #62

Comments

@spzhuang
Copy link

During run raw_pose_processing.ipynb, It report mistake.

# codes in raw_pose_processing.ipynb

for i in tqdm(range(total_amount)):
   source_path = index_file.loc[i]['source_path']
   new_name = index_file.loc[i]['new_name']
   data = np.load(source_path)
   start_frame = index_file.loc[i]['start_frame']
   end_frame = index_file.loc[i]['end_frame']
   if 'humanact12' not in source_path:
       if 'Eyes_Japan_Dataset' in source_path:
           data = data[3*fps:] # fps=20,它在上一个cell中定义
       if 'MPI_HDM05' in source_path:
           data = data[3*fps:]
       if 'TotalCapture' in source_path:
           data = data[1*fps:]
       if 'MPI_Limits' in source_path:
           data = data[1*fps:]
       if 'Transitions_mocap' in source_path:
           data = data[int(0.5*fps):]
       data = data[start_frame:end_frame]
       data[..., 0] *= -1
   
   data_m = swap_left_right(data)
#     save_path = pjoin(save_dir, )
   np.save(pjoin(save_dir, new_name), data)
   np.save(pjoin(save_dir, 'M'+new_name), data_m)

The Mistake:

---------------------------------------------------------------------------
FileNotFoundError                         Traceback (most recent call last)
/tmp/ipykernel_1288084/2659050203.py in 
      2     source_path = index_file.loc[i]['source_path']
      3     new_name = index_file.loc[i]['new_name']
----> 4     data = np.load(source_path)
      5     start_frame = index_file.loc[i]['start_frame']
      6     end_frame = index_file.loc[i]['end_frame']

/usr/local/anaconda3/envs/torch_render/lib/python3.7/site-packages/numpy/lib/npyio.py in load(file, mmap_mode, allow_pickle, fix_imports, encoding)
    415             own_fid = False
    416         else:
--> 417             fid = stack.enter_context(open(os_fspath(file), "rb"))
    418             own_fid = True
    419 

FileNotFoundError: [Errno 2] No such file or directory: '[./pose_data/humanact12/humanact12/P11G01R02F1812T1847A0402.npy](https://vscode-remote+ssh-002dremote-002b192-002e168-002e0-002e17.vscode-resource.vscode-cdn.net/home/jianchang/myproject/HumanML3D/pose_data/humanact12/humanact12/P11G01R02F1812T1847A0402.npy)'

Anying idea for the situation!

@EricGuo5513
Copy link
Owner

EricGuo5513 commented Apr 24, 2023 via email

@spzhuang
Copy link
Author

I searched the repository file carefully, but still found nothing about humanact12, even though I used the command find . -regex '. +?humanact12' .
Can you be more specific about the location of the dataset hhumanact12?

@EricGuo5513
Copy link
Owner

EricGuo5513 commented Apr 24, 2023 via email

@spzhuang
Copy link
Author

Thank you very much.
I have already remember some details about running script raw_pose_processing.ipynb.
When deal data from amass_data to pose_data, I meet a mistake, the code can't deal file likes "LICENSE.txt" which download from AMASS url. So I delete the pose_data file and all "LICENSE.txt", and then redeal the data from amass_data to pose_data. Hence, I found nothing about humanact12.zip.
Thank you again!
You can close this topic .

@EricGuo5513
Copy link
Owner

EricGuo5513 commented Apr 24, 2023 via email

@felixdivo felixdivo linked a pull request Jun 24, 2023 that will close this issue
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

Successfully merging a pull request may close this issue.

2 participants