mindspore.nn.LRN

class mindspore.nn.LRN(depth_radius=5, bias=1.0, alpha=1.0, beta=0.5, norm_region='ACROSS_CHANNELS')[source]

Local Response Normalization.

Warning

This interface is deprecated and will be removed after version 2.9.0.
LRN is deprecated on Ascend due to potential accuracy problem. It's recommended to use other normalization methods, e.g. mindspore.nn.BatchNorm1d , mindspore.nn.BatchNorm2d , mindspore.nn.BatchNorm3d.

Refer to mindspore.ops.lrn() for more details.

Supported Platforms:: GPU CPU

Examples

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