search

Chiaraplizz / ST-TR

Spatial Temporal Transformer Network for Skeleton-Based Activity Recognition
MIT License
299 stars 58 forks source link

Many files were not found while preparing the dataset. such as resource/NTU-RGB-D/samples_with_missing_skeletons.txt #22

Open 1274739295 opened 3 years ago

1274739295 commented 3 years ago

Hi Chiara, After reading your paper, I think this is a very meaningful study. I was trying to reproduce the results but I’m can’t find many files. 1.When I try the nut_gendata.py, the error is that No such file or directory:’resource/NTU-RGB-D/samples_with_missing_skeletons.txt’. For this problem, I copied the resource file in st-gcn. 2.When I try the nut_gen_bones.py, the error is that No such file or directory:’./xview/train_data_joint.npy’. 3.When I try the preprocess.py, the error is that No such file or directory:’../data/nturgbd_raw/samples_with_missing_skeletons.txt’. Can you give advice on how to solve these problems？ Thanks a lot， best

Chiaraplizz commented 3 years ago

Hi :)

Did you correctly set all paths? For error 2. it seems it cannot find the data you just created. As far as samples_with_missing_skeletons.txt, I am sorry I did not uploaded them (I will soon). Please, in the meanwhile, use the ones provided in st-gcn.

Kindly,

Chiara

1274739295 commented 3 years ago

Thank you very much for your answer. I used ST-GCN for the first file that could not be found, and the first question was solved. As for the second question, I would like to know:The ntu_gendata.py is used to create the joint as the preprocess.py is used to create the joint, so select either P or S to run, right?It would be even better if you could share the kinects-skeleton dataset.My e-mail address is 17864396525@163.com. Thanks a lot， best