MapLRN¶
Description¶
This module implements the operation of intra-channel local response normalization.
Initializing¶
def __init__(self, N=5, alpha=1e-4, beta=0.75, K=2.0, name=None):
Parameters
Parameter | Allowed types | Description | Default |
---|---|---|---|
N | int | Length of the side of the square area to normalize | 5 |
alpha | float | Bias | 1e-4 |
beta | float | Scale parameter | 0.75 |
K | float | Incremental coefficient | 2.0 |
name | str | Layer name | None |
Explanations
-
Examples¶
Necessary imports.
>>> import numpy as np
>>> from PuzzleLib.Backend import gpuarray
>>> from PuzzleLib.Modules import MapLRN
Info
gpuarray
is required to properly place the tensor in the GPU
>>> batchsize, maps, h, w = 1, 1, 10, 10
>>> data = gpuarray.to_gpu(np.random.randn(batchsize, maps, h, w).astype(np.float32))
>>> lrn = MapLRN()
>>> lrn(data)