LocalResponseNorm

class torch.nn.LocalResponseNorm(size, alpha=0.0001, beta=0.75, k=1.0) [source]

Applies local response normalization over an input signal.

The input signal is composed of several input planes, where channels occupy the second dimension. Applies normalization across channels.

$$b_{c} = a_{c}\left(k + \frac{\alpha}{n} \sum_{c'=\max(0, c-n/2)}^{\min(N-1,c+n/2)}a_{c'}^2\right)^{-\beta}$$

Parameters

• size (int) – amount of neighbouring channels used for normalization
• alpha (float) – multiplicative factor. Default: 0.0001
• beta (float) – exponent. Default: 0.75
• k (float) – additive factor. Default: 1

Shape:

• Input: $(N, C, *)$
• Output: $(N, C, *)$ (same shape as input)

Examples:

>>> lrn = nn.LocalResponseNorm(2)
>>> signal_2d = torch.randn(32, 5, 24, 24)
>>> signal_4d = torch.randn(16, 5, 7, 7, 7, 7)
>>> output_2d = lrn(signal_2d)
>>> output_4d = lrn(signal_4d)

extra_repr() [source]

Return the extra representation of the module.

forward(input) [source]

Runs the forward pass.

Return type

Tensor