Table Of Contents
Table Of Contents


mxnet.ndarray.InstanceNorm(data=None, gamma=None, beta=None, eps=_Null, out=None, name=None, **kwargs)

Applies instance normalization to the n-dimensional input array.

This operator takes an n-dimensional input array where (n>2) and normalizes the input using the following formula:

\[out = \frac{x - mean[data]}{ \sqrt{Var[data]} + \epsilon} * gamma + beta\]

This layer is similar to batch normalization layer (BatchNorm) with two differences: first, the normalization is carried out per example (instance), not over a batch. Second, the same normalization is applied both at test and train time. This operation is also known as contrast normalization.

If the input data is of shape [batch, channel, spacial_dim1, spacial_dim2, …], gamma and beta parameters must be vectors of shape [channel].

This implementation is based on paper:


Instance Normalization: The Missing Ingredient for Fast Stylization, D. Ulyanov, A. Vedaldi, V. Lempitsky, 2016 (arXiv:1607.08022v2).


// Input of shape (2,1,2)
x = [[[ 1.1,  2.2]],
     [[ 3.3,  4.4]]]

// gamma parameter of length 1
gamma = [1.5]

// beta parameter of length 1
beta = [0.5]

// Instance normalization is calculated with the above formula
InstanceNorm(x,gamma,beta) = [[[-0.997527  ,  1.99752665]],
                              [[-0.99752653,  1.99752724]]]

Defined in src/operator/

  • data (NDArray) – An n-dimensional input array (n > 2) of the form [batch, channel, spatial_dim1, spatial_dim2, …].

  • gamma (NDArray) – A vector of length ‘channel’, which multiplies the normalized input.

  • beta (NDArray) – A vector of length ‘channel’, which is added to the product of the normalized input and the weight.

  • eps (float, optional, default=0.001) – An epsilon parameter to prevent division by 0.

  • out (NDArray, optional) – The output NDArray to hold the result.


out – The output of this function.

Return type

NDArray or list of NDArrays