chrismessenger
Results
3
comments of
chrismessenger
Also, the self.nonlinearity_mean = tf.clip_by_value is never used so can be removed.
You can also delete the commented out "make positive definite covariance matrix code"
Marlin, I think this is because the sky parameters output from the decoder are designed to be 3D in the sense that they are modelled using the Fisher Von Mises...