LocalResponseNorm#

class LocalResponseNorm(kernel_size=5, k=2.0, alpha=1e-4, beta=0.75, **kwargs)[源代码]#

对输入 Tensor 执行 LocalResponse 正则化。

参数:

  • kernel_size (int) – 指定 LRN 的 kernel size。

  • k (float) – 超参数 k，默认值为 2.0

  • alpha (float) – 超参数 alpha，默认值为 1e-4

  • beta (float) – 超参数 beta，默认值为 0.75

示例

>>> import numpy as np
>>> inp = Tensor(np.arange(25, dtype=np.float32).reshape(1,1,5,5))
>>> GT = np.array([[[[ 0.,         0.999925,   1.9994003,  2.9979765,  3.9952066],
...                  [ 4.9906454,  5.983851,   6.974385,   7.961814,   8.945709 ],
...                  [ 9.925651,  10.90122,   11.872011,  12.837625,  13.7976675],
...                  [14.751757,  15.699524,  16.640602,  17.574642,  18.501305 ],
...                  [19.420258,  20.331186,  21.233786,  22.127764,  23.012836 ]]]])
>>> op = M.LocalResponseNorm(kernel_size=3, k=1.0, alpha=1e-4, beta=0.75)
>>> out = op(inp)
>>> np.testing.assert_allclose(GT, out.numpy(), rtol=1e-6, atol=1e-6)