Closed IssaIssa1 closed 5 years ago
You may need to regenerate the data from the raw skeletons and filter out the unwanted classes, and train on the filtered data.
See this line in ntu_gen_joint_data.py
:
action_class = int(filename[filename.find('A') + 1:filename.find('A') + 4])
How can I train the DGNN on selected number of classes using NTU dataset instead in training it on all the data?