gen_joint_data.py

[itisthoughttobemaeri]

Hello,

Thanks for publishing the code of your research. While trying to reproduce the results, the command python3 gen_joint_data.py gets stuck at the element #1370/35208 with the following error:

python3 gen_joint_data.py
xsub train
4%|██▍ | 1370/35208 [00:29<11:56, 47.21it/s]
Traceback (most recent call last):
File "/Users/mari/Desktop/ST-GCN-master/data_gen/gen_joint_data.py", line 164, in
gendata(
File "/Users/mari/Desktop/ST-GCN-master/data_gen/gen_joint_data.py", line 140, in gendata
data = read_xyz(os.path.join(data_path, s), max_body=max_body_kinect, num_joint=num_joint)
File "/Users/mari/Desktop/ST-GCN-master/data_gen/gen_joint_data.py", line 77, in read_xyz
seq_info = read_skeleton_filter(file)
File "/Users/mari/Desktop/ST-GCN-master/data_gen/gen_joint_data.py", line 28, in read_skeleton_filter
skeleton_sequence['numFrame'] = int(f.readline())
ValueError: invalid literal for int() with base 10: '\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x0

I was wondering if this had something to do with the samples_missing_skeletons.txt file.
I got the dataset from the ROSE lab (https://rose1.ntu.edu.sg/dataset/actionRecognition/).

Thanks in advance

[itskalvik]

Perhaps it's a bad data file, I didn't add enough sanity checks in my code to handle such things. Try deleting that one file or use a different subset of the dataset. Hope that helps :)