chainer.functions.layer_normalization¶

chainer.functions.layer_normalization(x, gamma, beta, eps=1e-05)[source]¶

Layer normalization.

This function implements a “layer normalization” which normalizes the input units by statistics that are computed along the second axis, scales and shifts them.

Parameters

x (Variable or N-dimensional array) – Batch vectors. Shape of this value must be (batch_size, unit_size), e.g., the output of linear().
gamma (Variable or N-dimensional array) – Scaling vectors.
beta (Variable or N-dimensional array) – Shifting vectors.

Returns

The output variable which has the same shape as \(x\).

Return type

Variable

See: Layer Normalization