chainer.functions.gaussian¶
-
chainer.functions.
gaussian
(mean, ln_var, *, eps=None, return_eps=False)[source]¶ Gaussian sampling function.
This function takes a mean \(\mu\) and the logarithm of a variance \(\log(\sigma^2)\) as inputs and outputs a sample drawn from a Gaussian distribution \(N(\mu, \sigma)\).
The inputs must have the same shape.
Parameters: - mean (Variable) – Input variable representing the mean \(\mu\).
- ln_var (Variable) – Input variable representing the logarithm of a variance \(\log(\sigma^2)\).
- eps (ndarray or None) – The eps value to be used.
You do not have to specify this value, unless you need to make
results deterministic.
If
eps
is not specified or set toNone
, an eps value will be generated randomly. The shape and dtype must be the same asln_var
and should be on the same device. - return_eps (bool) – If
True
, the eps value used in this function is returned together with the output variable. The returned eps can later be reused by passing it to theeps
argument.
Returns: When
return_eps
isFalse
(default), returns the output variable with the shape ofmean
and/orln_var
. WhenTrue
, returns the tuple of the output variable and eps (ndarray). The eps will be on the same device as the input (ln_var
).Return type: