RuntimeError: running_mean should contain 126 elements not 63 (example).

[JasOlean]

What is your elements for number of joints (18)?
When I run your code, I got this error " RuntimeError: running_mean should contain 126 elements not 63". 63 means I change number of node.
How to adjust these elements and how to get your elements 126 for your experiment?

[lshiwjx]

The number of elements for running_mean = num_person * in_channels * num_point

[JasOlean]

When I run your kinetics data, I changed num_person = 1, in_channels = 3, num_point = 18. running_mean value is 54. In that case, I got this error "RuntimeError: running_mean should contain 108 elements not 54".
What has happened? why they said should contain 108 elements when num_person = 1?

[lshiwjx]

It should be 54, maybe the param num_person is not successfully passed to the model.
You can try to check the data shape.