Spatial-Temporal Graph Convolutional Framework for Yoga Action Recognition and Grading

Table 3

Training parameter settings.

Parameter	Value
Epoch	20
Dropout rate	0.5
Initial learning rate	0.05
Learning rate (epoch = 30)	0.01
Learning rate (epoch = 50)	0.002
Learning rate (epoch = 60)	0.0004
Weight attenuation coefficient	0.0002
Momentum	0.9