|View source on GitHub|
Create a random variable for VonMisesFisher.
tfp.edward2.VonMisesFisher( *args, **kwargs )
See VonMisesFisher for more details.
Original Docstring for Distribution
Creates a new
Tensorwith shape [B1, ... Bn, D]. A unit vector indicating the mode of the distribution, or the unit-normalized direction of the mean. (This is not in general the mean of the distribution; the mean is not generally in the support of the distribution.) NOTE:
Dis currently restricted to <= 5.
Tensorhaving batch shape [B1, ... Bn] broadcastable with
mean_direction. The level of concentration of samples around the
concentration=0indicates a uniform distribution over the unit hypersphere, and
Deterministicdistribution (delta function) at
Truedistribution parameters are checked for validity despite possibly degrading runtime performance. When
Falseinvalid inputs may silently render incorrect outputs.
True, statistics (e.g., mean, mode, variance) use the value "
NaN" to indicate the result is undefined. When
False, an exception is raised if one or more of the statistic's batch members are undefined.
strname prefixed to Ops created by this class.
ValueError: For known-bad arguments, i.e. unsupported event dimension.