local_response_norm

dragon.nn.local_response_norm(
  inputs,
  size=5,
  alpha=0.0001,
  beta=0.75,
  bias=1.0,
  data_format='NCHW',
  **kwargs
)[source]

Apply the local response normalization. [Krizhevsky et.al, 2012].

The normalization is defined as:

\[out_{i} = x_{i}\left(k + \frac{\alpha}{n} \sum_{j=\max(0, i-n/2)}^{\min(N-1,i+n/2)}x_{j}^2 \right)^{-\beta} \]
Parameters:
  • inputs (dragon.Tensor) – The input tensor.
  • size (int, optional, default=5) – The number of neighbouring channels to sum over.
  • alpha (float, optional, default=0.0001) – The scale value \(\alpha\).
  • beta (float, optional, default=0.75) – The exponent value \(\beta\).
  • bias (float, optional, default=1.) – The bias constant \(k\).
  • data_format ({'NCHW', 'NHWC'}, optional) – The optional data format.
Returns:

dragon.Tensor – The output tensor.