def ae2(data):
"""This one uses an Autoencode layer. This layer is a part of the graph and does not need a specific traget"""
miniBatchSize = 1
ls = MS.GradientDescent(lr=0.1)
cost = MC.MeanSquaredError()
i = ML.Input(8, name='inp')
h = ML.Hidden(3,
activation=MA.ReLU(),
initializations=[MI.SmallUniformWeights(),
MI.ZeroBias()],
name="hid")
o = ML.Autoencode(
i.name,
activation=MA.ReLU(),
initializations=[MI.SmallUniformWeights(),
MI.ZeroBias()],
learningScenario=ls,
costObject=cost,
name="out")
ae = i > h > o
# ae.init()
# o.train.printGraph()
for e in xrange(2000):
for i in xrange(0, len(data), miniBatchSize):
ae.train(o, inp=data[i:i + miniBatchSize])
return ae, o
def ae1(data):
'''Using a regression layer. This layer needs an explicit target'''
miniBatchSize = 2
ls = MS.GradientDescent(lr=0.1)
cost = MC.MeanSquaredError()
i = ML.Input(8, name='inp')
h = ML.Hidden(3,
activation=MA.ReLU(),
initializations=[MI.SmallUniformWeights(),
MI.ZeroBias()],
name="hid")
o = ML.Regression(
8,
activation=MA.ReLU(),
initializations=[MI.SmallUniformWeights(),
MI.ZeroBias()],
learningScenario=ls,
costObject=cost,
name="out")
ae = i > h > o
for e in xrange(1000):
for i in xrange(0, len(data), miniBatchSize):
ae.train(o,
inp=data[i:i + miniBatchSize],
targets=data[i:i + miniBatchSize])
return ae, o
def test_ae(self):
data = []
for i in xrange(8):
zeros = numpy.zeros(8)
zeros[i] = 1
data.append(zeros)
ls = MS.GradientDescent(lr=0.1)
cost = MC.MeanSquaredError()
i = ML.Input(8, name='inp')
h = ML.Hidden(3, activation=MA.ReLU(), name="hid")
o = ML.Regression(8,
activation=MA.ReLU(),
learningScenario=ls,
costObject=cost,
name="out")
ae = i > h > o
miniBatchSize = 2
for e in xrange(2000):
for i in xrange(0, len(data), miniBatchSize):
ae.train(o,
inp=data[i:i + miniBatchSize],
targets=data[i:i + miniBatchSize])
res = ae.propagate(o, inp=data)["outputs"]
for i in xrange(len(res)):
self.assertEqual(numpy.argmax(data[i]), numpy.argmax(res[i]))
def test_ae(self) :
data = []
for i in xrange(8) :
zeros = numpy.zeros(8)
zeros[i] = 1
data.append(zeros)
ls = MS.GradientDescent(lr = 0.1)
cost = MC.MeanSquaredError()
i = ML.Input(8, name = 'inp')
h = ML.Hidden(3, activation = MA.ReLU(), initializations=[MI.SmallUniformWeights(), MI.ZeroBias()], name = "hid")
o = ML.Autoencode(targetLayerName = "inp", activation = MA.ReLU(), initializations=[MI.SmallUniformWeights(), MI.ZeroBias()], learningScenario = ls, costObject = cost, name = "out" )
ae = i > h > o
miniBatchSize = 1
for e in xrange(2000) :
for i in xrange(0, len(data), miniBatchSize) :
ae.train(o, inp = data[i:i+miniBatchSize])
res = ae.propagate(o, inp = data)["outputs"]
for i in xrange(len(res)) :
self.assertEqual( numpy.argmax(data[i]), numpy.argmax(res[i]))
def test_ae_reg(self):
powerOf2 = 3
nbUnits = 2**powerOf2
data = []
for i in xrange(nbUnits):
zeros = numpy.zeros(nbUnits)
zeros[i] = 1
data.append(zeros)
ls = MS.GradientDescent(lr=0.1)
cost = MC.MeanSquaredError()
i = ML.Input(nbUnits, name='inp')
h = ML.Hidden(powerOf2,
activation=MA.ReLU(),
initializations=[
MI.Uniform('W', small=True),
MI.SingleValue('b', 0)
],
name="hid")
o = ML.Regression(nbUnits,
activation=MA.ReLU(),
initializations=[
MI.Uniform('W', small=True),
MI.SingleValue('b', 0)
],
learningScenari=[ls],
cost=cost,
name="out")
ae = i > h > o
ae.init()
miniBatchSize = 1
for e in xrange(2000):
for i in xrange(0, len(data), miniBatchSize):
miniBatch = data[i:i + miniBatchSize]
ae["out"].train({
"inp.inputs": miniBatch,
"out.targets": miniBatch
})["out.drive.train"]
res = ae["out"].propagate["test"]({
"inp.inputs": data
})["out.propagate.test"]
for i in xrange(len(res)):
self.assertEqual(numpy.argmax(data[i]), numpy.argmax(res[i]))
def test_multiout_fctmixin(self):
i = ML.Input(1, name='inp')
o1 = ML.Autoencode(targetLayer=i,
activation=MA.Tanh(),
learningScenari=[MS.GradientDescent(lr=0.1)],
cost=MC.MeanSquaredError(),
name="out1")
o2 = ML.Regression(1,
activation=MA.Tanh(),
learningScenari=[MS.GradientDescent(lr=0.2)],
cost=MC.MeanSquaredError(),
name="out2")
i > o1
ae = i > o2
ae.init()
preOut1 = ae["out1"].test({"inp.inputs": [[1]]})["out1.drive.test"]
preOut2 = ae["out2"].test({
"inp.inputs": [[1]],
"out2.targets": [[1]]
})["out2.drive.test"]
ae["out1"].train({"inp.inputs": [[1]]})["out1.drive.train"]
self.assertTrue(
preOut1 > ae["out1"].test({"inp.inputs": [[1]]})["out1.drive.test"]
)
self.assertTrue(preOut2 == ae["out2"].test({
"inp.inputs": [[1]],
"out2.targets": [[1]]
})["out2.drive.test"])
preOut1 = ae["out1"].test({"inp.inputs": [[1]]})["out1.drive.test"]
preOut2 = ae["out2"].test({
"inp.inputs": [[1]],
"out2.targets": [[1]]
})["out2.drive.test"]
ae["out2"].train({
"inp.inputs": [[1]],
"out2.targets": [[1]]
})["out2.drive.train"]
self.assertTrue(preOut1 == ae["out1"].test({"inp.inputs": [[1]]})
["out1.drive.test"])
self.assertTrue(preOut2 > ae["out2"].test({
"inp.inputs": [[1]],
"out2.targets": [[1]]
})["out2.drive.test"])
preOut1 = ae["out1"].test({"inp.inputs": [[1]]})["out1.drive.test"]
preOut2 = ae["out2"].test({
"inp.inputs": [[1]],
"out2.targets": [[1]]
})["out2.drive.test"]
fct = ae["out1"].train + ae["out2"].train + ae["inp"].propagate["train"]
ret = fct({"inp.inputs": [[1]], "out2.targets": [[1]]})
self.assertEqual(len(ret), 3)
self.assertTrue(
preOut1 > ae["out1"].test({"inp.inputs": [[1]]})["out1.drive.test"]
)
self.assertTrue(preOut2 > ae["out2"].test({
"inp.inputs": [[1]],
"out2.targets": [[1]]
})["out2.drive.test"])
