def __init__(self,
inputDim,
convFilterNum,
convFilterDim,
convImageSize,
poolFilterDim,
poolImageSize,
hiddenDim,
outputDim,
seed=1):
#畳み込み+プーリング付き３層ニューラルネット
self.inputLayer = layer.InputLayer(inputDim)
self.convLayer = layer.ConvolutionalLayer(convFilterNum, convFilterDim,
convImageSize,
self.inputLayer, seed)
self.poolLayer = layer.PoolingLayer(poolFilterDim, poolImageSize,
self.convLayer)
self.hiddenLayer = layer.HiddenLayer(hiddenDim, self.poolLayer, seed)
self.outputLayer = layer.OutputLayer(outputDim, self.hiddenLayer, seed)
self.hiddenLayer.setActivator(util.relu)
self.hiddenLayer.setBackPropagator(learning.backPropReLU)
# 正解データ
self.answer = np.zeros(outputDim)
def __init__(self, inputDim, hiddenDim, outputDim, seed=1):
# 三層ニューラルネットワーク
self.inputLayer = layer.InputLayer(inputDim)
self.hiddenLayer = layer.HiddenLayer(hiddenDim, self.inputLayer, seed)
self.outputLayer = layer.OutputLayer(outputDim, self.hiddenLayer, seed)
# 正解データ
self.answer = np.zeros(outputDim)
def __init__(self, inputDim, hiddenDim, outputDim, seed=1):
# 三層ニューラルネットワーク
self.inputLayer = layer.InputLayer(inputDim)
self.hiddenLayer = layer.HiddenLayer(hiddenDim, self.inputLayer, seed)
self.outputLayer = layer.OutputLayer(outputDim, self.hiddenLayer, seed)
self.hiddenLayer.setActivator(util.relu)
self.hiddenLayer.setBackPropagator(learning.backPropReLU)
# 正解データ
self.answer = np.zeros(outputDim)
def __init__(self, layers):
# 输入一个list，存放每一个hiddenLayer的节点数
self.network = []
self.network.append(layer.InputLayer()) # 输入层
i = 0
while i < len(layers):
self.network.append(
layer.HiddenLayer(layers[i], self.network[i], None))
i = i + 1
self.network.append(layer.OutputLayer(self.network[i]))
i = 0
while i < len(self.network) - 1:
self.network[i].next_layer = self.network[i + 1]
if i != 0:
self.network[i].initialize() # 对中间层重新进行初始化
i = i + 1
self.network[-1].initialize()
import ioex
import layer
import util
print("### task1 ###")
# 入出力準備
inputM = ioex.InputManager()
outputM = ioex.OutputManager()
testingData = inputM.getMnistTestingData()
# ３層ニューラルネットワーク
inputLayer = layer.InputLayer(28 * 28)
hiddenLayer = layer.HiddenLayer(50, inputLayer, 1, 1)
outputLayer = layer.OutputLayer(10, hiddenLayer, 1, 1)
# ニューラルネットワークの設定
#outputLayer.setActivator(util.correctedSoftmax)
#入出力
loop = True
while (loop):
# 入力
targetNum = inputM.selectNumber()
sample = testingData.getSingleData(targetNum)
inputLayer.setInput(sample.getImage())
# 出力
result = outputLayer.calculate()
outputM.printMaxLikelihood(result)
print(result)
def _set_layers(self):
last_layer = self.depth - 1
self.layers.append(layer.InputLayer(self.form[0]))
for i in range(1, last_layer):
self.layers.append(layer.HiddenLayer(self.form[i], [], []))
self.layers.append(layer.OutputLayer(self.form[last_layer], [], []))
def inputToHiddenTest():
inputLayer = inputLayerTest()
hiddenLayer = layer.HiddenLayer(9, inputLayer)
hiddenLayer.setWeight(SAMPLE_WEIGHT)
hiddenLayer.setShift(SAMPLE_SHIFT)
print(hiddenLayer.calculate())
def hiddenLayerTest():
prev = layer.Layer(10)
hiddenLayer = layer.HiddenLayer(5, prev)
hiddenLayer.confirmParameters()
import net import layer import random import neuron import sys import time print "Initialising the training data (golden standard)" netInputVector = [[0.05, 0.1], [0.1, 0.2]] netOutputVector = [[0.01, 0.99], [0.04, 0.99]] print "Setting up the net" net = net.Net() inputLayer = layer.InputLayer(2, net, neuron.SigmoidNeuron) net.setInputLayer(inputLayer) hiddenLayer1 = layer.HiddenLayer(3, net, neuron.SigmoidNeuron) net.addHiddenLayer(hiddenLayer1) hiddenLayer2 = layer.HiddenLayer(5, net, neuron.SigmoidNeuron) net.addHiddenLayer(hiddenLayer2) outputLayer = layer.OutputLayer(2, net, neuron.SigmoidNeuron) net.setOutputLayer(outputLayer) print "Training the net" #for index in range(0, len(netInputVector)): # net.inputLayer.setActivationVector(netInputVector[index]) # net.perform() # error = net.outputLayer.error(netOutputVector[index]) # epoch = 1 # while error > 0.01: # net.backpropagate(netOutputVector[index]) # net.perform()
def test_hidden_layer():
print "Testing hidden layer..."
for k in xrange(5):
print "Layer %i..." % k
# random parameters
input_dim = np.random.randint(1, 100)
output_dim = np.random.randint(1, 100)
bias = np.random.randint(2)
activation = 'tanh' if np.random.randint(2) else 'sigmoid'
# hidden layer
hidden_layer = layer.HiddenLayer(input_dim, output_dim, bias,
activation, 'test')
for i in xrange(20):
print "%i" % i,
# tests for dimension 1, 2, 3 and 4
if i % 4 == 0:
input = T.vector('input_test')
input_value = np.random.rand(input_dim).astype(floatX)
elif i % 4 == 1:
input = T.matrix('input_test')
input_value = np.random.rand(
np.random.randint(100),
input_dim
).astype(floatX)
elif i % 4 == 2:
input = T.tensor3('input_test')
input_value = np.random.rand(
np.random.randint(50),
np.random.randint(50),
input_dim
).astype(floatX)
else:
input = T.tensor4('input_test')
input_value = np.random.rand(
np.random.randint(20),
np.random.randint(20),
np.random.randint(20),
input_dim
).astype(floatX)
output = hidden_layer.link(input)
expected_value = np.dot(
input_value,
hidden_layer.weights.get_value()
)
if bias:
expected_value += hidden_layer.bias.get_value()
if activation == 'tanh':
expected_value = np.tanh(expected_value)
else:
expected_value = expit(expected_value)
assert expected_value.shape == input_value.shape[:-1] + (output_dim,)
np.testing.assert_array_almost_equal(
output.eval({input: input_value}),
expected_value
)
print "OK"
print "All tests ran successfully for Hidden Layer."