本文整理汇总了Python中Network.initNetwork方法的典型用法代码示例。如果您正苦于以下问题：Python Network.initNetwork方法的具体用法？Python Network.initNetwork怎么用？Python Network.initNetwork使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类Network的用法示例。
在下文中一共展示了Network.initNetwork方法的1个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: Network
# 需要导入模块: import Network [as 别名]
# 或者: from Network import initNetwork [as 别名]
PatchMode = 'Adjacent' #
ImageType = 'Color'
NetworkMode = True # training is set true
#For a Node: specify Your Algorithm Choice and Corresponding parameters
AlgorithmChoice = 'Clustering'
AlgParams = {'mr': 0.01, 'vr': 0.01, 'sr': 0.001, 'DIMS': [], 'CENTS': [], 'node_id': [],
'NumCentsPerLayer': NumCentsPerLayer}
#Declare a Network Object
DESTIN = Network(numLayers, AlgorithmChoice, AlgParams, NumNodesPerLayer, PatchMode, ImageType)
DESTIN.setMode(NetworkMode) #training or not
DESTIN.setLowestLayer(0)
#Load Data
[data, labels] = loadCifar(10) # loads cifar_data_batch_1
#data = np.random.rand(5,32*32*3)
#Initialize Network; there is is also a layer-wise initialization option
DESTIN.initNetwork()
#data.shape[0]
for I in range(data.shape[0]):# For Every image in the data set
if I%1000 == 0:
print("Training Iteration Number %d" % I)
for L in range(DESTIN.NumberOfLayers):
if L == 0:
img = data[I][:].reshape(32,32,3)
DESTIN.Layers[0][L].trainTypicalNode(img,[4,4])
else:
DESTIN.Layers[0][L].trainTypicalNode(DESTIN.Layers[0][L-1].Nodes,[2,2])
DESTIN.Layers[0][L].shareCentroids()
DESTIN.updateBeliefExporter()
DESTIN.dumpBelief(2)
DESTIN.cleanBeliefExporter()#Get rid-off accumulated training beliefs
print("Testing Started")