CrossMapLRN

Description

Info

Parent class: LRN

Derived classes: -

This module implements the operation of cross-map 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	Number of channels to be summed	5
alpha	float	Shift	1e-4
beta	float	Scale parameter	0.75
K	float	Additional 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 CrossMapLRN

Info

gpuarray is required to properly place the tensor in the GPU.

batchsize, maps, h, w = 1, 10, 2, 2
data = gpuarray.to_gpu(np.random.randn(batchsize, maps, h, w).astype(np.float32))
lrn = CrossMapLRN()
lrn(data)