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 and beta.
• axis (int, optional, default=-1) – The channel axis.
• epsilon (float, optional, default=1e-5) – The value to $\epsilon$.

Returns:

dragon.Tensor – The output tensor.