Closed aviziskind closed 5 years ago
In the nets.py, in the calculation of pose, you multiply by a small constant of 0.01:
# Empirically we found that scaling by a small constant # facilitates training. pose_final = 0.01 * tf.reshape(pose_avg, [-1, num_source, 6])
I am curious how you came to discover this... and if you have any intuition as to why this should help to facilitate training?
The intuition was that since we are sampling consecutive frames, the pose change should be relatively small. So multiplying by a small constant incorporates such prior information.
In the nets.py, in the calculation of pose, you multiply by a small constant of 0.01:
I am curious how you came to discover this... and if you have any intuition as to why this should help to facilitate training?