mindspore.ops.LRN

class mindspore.ops.LRN(depth_radius=5, bias=1.0, alpha=1.0, beta=0.5, norm_region='ACROSS_CHANNELS')

Local Response Normalization.

Warning

LRN is deprecated on Ascend due to potential accuracy problem. It's recommended to use other normalization methods, e.g. mindspore.ops.BatchNorm.

$$b_c=a_c{(k+\frac{\alpha }{n}\sum _{c^{\prime }=max(0,c-n/2)}^{min(N-1,c+n/2)}{a}_{c^{\prime }}^2)}^{-\beta }$$

where the $a_c$ indicates the specific value of the pixel corresponding to $c$ in feature map; where the $n/2$ indicates the depth_radius; where the $k$ indicates the bias; where the $\alpha$ indicates the alpha; where the $\beta$ indicates the 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 4-D Tensor with float16 or float32 data type.

Outputs:

Tensor, with the same shape and data type as x.

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:

GPU CPU

Examples

>>> import mindspore
>>> import numpy as np
>>> from mindspore import Tensor, ops
>>> x = Tensor(np.array([[[[0.1], [0.2]],
...                       [[0.3], [0.4]]]]), mindspore.float32)
>>> lrn = ops.LRN()
>>> output = lrn(x)
>>> print(output)
[[[[0.09534626]
   [0.1825742 ]]
  [[0.2860388 ]
   [0.3651484 ]]]]