instance_norm¶
dragon.nn.
instance_norm
(
inputs,
axis=- 1,
epsilon=1e-05,
**kwargs
)[source]¶Apply the instance normalization. [Ulyanov et.al, 2016]
The normalization is defined as:
\[y = \frac{x - \mathrm{E}[x]} {\sqrt{\mathrm{Var}[x] + \epsilon}} * \gamma + \beta \]- Parameters:
- inputs (Sequence[dragon.Tensor]) – The tensor
x
,gamma
andbeta
. - axis (int, optional, default=-1) – The channel axis.
- epsilon (float, optional, default=1e-5) – The value to \(\epsilon\).
- inputs (Sequence[dragon.Tensor]) – The tensor
- Returns:
dragon.Tensor – The output tensor.