Python generateNoisySines Examples

Example #1

File: example_rnn.py Project: fh-wedel/pybrain

# Example script for recurrent network usage in PyBrain.
__author__ = "Martin Felder"
__version__ = '$Id$'

from pylab import plot, hold, show
from scipy import sin, rand, arange
from pybrain.datasets            import SequenceClassificationDataSet
from pybrain.structure.modules   import LSTMLayer, SoftmaxLayer
from pybrain.supervised          import RPropMinusTrainer
from pybrain.tools.validation    import testOnSequenceData
from pybrain.tools.shortcuts     import buildNetwork

from datasets import generateNoisySines

# create training and test data
trndata = generateNoisySines(50, 40)
trndata._convertToOneOfMany( bounds=[0.,1.] )
tstdata = generateNoisySines(50, 20)
tstdata._convertToOneOfMany( bounds=[0.,1.] )

# construct LSTM network - note the missing output bias
rnn = buildNetwork( trndata.indim, 5, trndata.outdim, hiddenclass=LSTMLayer, outclass=SoftmaxLayer, outputbias=False, recurrent=True)

# define a training method
trainer = RPropMinusTrainer( rnn, dataset=trndata, verbose=True )
# instead, you may also try
##trainer = BackpropTrainer( rnn, dataset=trndata, verbose=True, momentum=0.9, learningrate=0.00001 )

# carry out the training
for i in range(100):
    trainer.trainEpochs( 2 )

Example #2

File: exampleRNN.py Project: chenzhikuo1/OCR-Python

# Example script for recurrent network usage in PyBrain.
__author__ = "Martin Felder"
__version__ = '$Id$'

from pylab import plot, hold, show
from scipy import sin, rand, arange
from pybrain.datasets import SequenceClassificationDataSet
from pybrain.structure.modules import LSTMLayer, SoftmaxLayer
from pybrain.supervised import RPropMinusTrainer
from pybrain.tools.validation import testOnSequenceData
from pybrain.tools.shortcuts import buildNetwork

from datasets import generateNoisySines

# create training and test data
trndata = generateNoisySines(50, 40)
trndata._convertToOneOfMany(bounds=[0., 1.])
tstdata = generateNoisySines(50, 20)
tstdata._convertToOneOfMany(bounds=[0., 1.])

# construct LSTM network - note the missing output bias
rnn = buildNetwork(trndata.indim,
                   5,
                   trndata.outdim,
                   hiddenclass=LSTMLayer,
                   outclass=SoftmaxLayer,
                   outputbias=False,
                   recurrent=True)

# define a training method
trainer = RPropMinusTrainer(rnn, dataset=trndata, verbose=True)

Example #3

File: example_rnn.py Project: ThomasRouvinez/UserRecognizer

# Example script for recurrent network usage in PyBrain.
__author__ = "Martin Felder"
__version__ = '$Id$'

from pylab import plot, hold, show
from scipy import sin, rand, arange
from pybrain.datasets            import SequenceClassificationDataSet
from pybrain.structure.modules   import LSTMLayer, SoftmaxLayer
from pybrain.supervised          import RPropMinusTrainer
from pybrain.tools.validation    import testOnSequenceData
from pybrain.tools.shortcuts     import buildNetwork

from datasets import generateNoisySines

# create training and test data
trndata = generateNoisySines(10, 8)
trndata._convertToOneOfMany(bounds=[0.,1.])
tstdata = generateNoisySines(50, 20)
tstdata._convertToOneOfMany(bounds=[0.,1.])

# construct LSTM network - note the missing output bias
rnn = buildNetwork( trndata.indim, 5, trndata.outdim, hiddenclass=LSTMLayer, outclass=SoftmaxLayer, outputbias=False, recurrent=True)

# define a training method
trainer = RPropMinusTrainer( rnn, dataset=trndata, verbose=True )
# instead, you may also try
##trainer = BackpropTrainer( rnn, dataset=trndata, verbose=True, momentum=0.9, learningrate=0.00001 )

# carry out the training
for i in xrange(100):
    trainer.trainEpochs( 2 )