mindspore.ops.LRN

class mindspore.ops.LRN(*args, **kwargs)

Local Response Normalization.

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

Parameters

• depth_radius (int) – Half-width of the 1-D normalization window with the shape of 0-D. Default: 5.

• bias (float) – An offset (usually positive to avoid dividing by 0). Default: 1.0.

• alpha (float) – A scale factor, usually positive. Default: 1.0.

• beta (float) – An exponent. Default: 0.5.

• norm_region (str) – Specifies normalization region. Options: “ACROSS_CHANNELS”. Default: “ACROSS_CHANNELS”.

Inputs:

• x (Tensor) - A 4D Tensor with float16 or float32 data type.

Outputs:

Tensor, with the same shape and data type as the input tensor.

Raises

• TypeError – If depth_radius is not an int.

• TypeError – If bias, alpha or beta is not a float.

• TypeError – If norm_region is not a str.

• TypeError – If x is not a Tensor.

Supported Platforms:

Ascend

Examples

>>> x = Tensor(np.random.rand(1, 2, 2, 2), mindspore.float32)
>>> lrn = ops.LRN()
>>> output = lrn(x)
>>> print(output.shape)
(1, 2, 2, 2)