def buildSharedCrossedNetwork():
""" build a network with shared connections. Two hiddne modules are symetrically linked, but to a different
input neuron than the output neuron. The weights are random. """
N = FeedForwardNetwork('shared-crossed')
h = 1
a = LinearLayer(2, name='a')
b = LinearLayer(h, name='b')
c = LinearLayer(h, name='c')
d = LinearLayer(2, name='d')
N.addInputModule(a)
N.addModule(b)
N.addModule(c)
N.addOutputModule(d)
m1 = MotherConnection(h)
m1.params[:] = scipy.array((1, ))
m2 = MotherConnection(h)
m2.params[:] = scipy.array((2, ))
N.addConnection(SharedFullConnection(m1, a, b, inSliceTo=1))
N.addConnection(SharedFullConnection(m1, a, c, inSliceFrom=1))
N.addConnection(SharedFullConnection(m2, b, d, outSliceFrom=1))
N.addConnection(SharedFullConnection(m2, c, d, outSliceTo=1))
N.sortModules()
return N
def buildSimpleBorderSwipingNet(size = 3, dim = 3, hsize = 1, predefined = {}):
""" build a simple swiping network,of given size and dimension, using linear inputs and output"""
# assuming identical size in all dimensions
dims = tuple([size]*dim)
# also includes one dimension for the swipes
hdims = tuple(list(dims)+[2**dim])
inmod = LinearLayer(size**dim, name = 'input')
inmesh = ModuleMesh.viewOnFlatLayer(inmod, dims, 'inmesh')
outmod = LinearLayer(size**dim, name = 'output')
outmesh = ModuleMesh.viewOnFlatLayer(outmod, dims, 'outmesh')
hiddenmesh = ModuleMesh.constructWithLayers(TanhLayer, hsize, hdims, 'hidden')
return BorderSwipingNetwork(inmesh, hiddenmesh, outmesh, predefined = predefined)
def buildSlicedNetwork():
""" build a network with shared connections. Two hiddne modules are symetrically linked, but to a different
input neuron than the output neuron. The weights are random. """
N = FeedForwardNetwork('sliced')
a = LinearLayer(2, name = 'a')
b = LinearLayer(2, name = 'b')
N.addInputModule(a)
N.addOutputModule(b)
N.addConnection(FullConnection(a, b, inSliceTo=1, outSliceFrom=1))
N.addConnection(FullConnection(a, b, inSliceFrom=1, outSliceTo=1))
N.sortModules()
return N
def _buildCaptureNetwork(self):
# the input is a 2D-mesh (as a view on a flat input layer)
inmod = LinearLayer(self.insize * self.size * self.size, name='input')
inmesh = ModuleMesh.viewOnFlatLayer(inmod, (self.size, self.size),
'inmesh')
# the output is a 2D-mesh (as a view on a flat sigmoid output layer)
outmod = self.outcomponentclass(self.outputs * self.size * self.size,
name='output')
outmesh = ModuleMesh.viewOnFlatLayer(outmod, (self.size, self.size),
'outmesh')
if self.componentclass is MDLSTMLayer:
c = lambda: MDLSTMLayer(self.hsize, 2, self.peepholes).meatSlice()
hiddenmesh = ModuleMesh(c, (self.size, self.size, 4),
'hidden',
baserename=True)
else:
hiddenmesh = ModuleMesh.constructWithLayers(
self.componentclass, self.hsize, (self.size, self.size, 4),
'hidden')
self._buildBorderStructure(inmesh, hiddenmesh, outmesh)
# add the identity connections for the states
for m in self.modules:
if isinstance(m, MDLSTMLayer):
tmp = m.stateSlice()
index = 0
for c in list(self.connections[m]):
if isinstance(c.outmod, MDLSTMLayer):
self.addConnection(
IdentityConnection(
tmp,
c.outmod.stateSlice(),
outSliceFrom=self.hsize * (index),
outSliceTo=self.hsize * (index + 1)))
index += 1
# direct connections between input and output
if self.directlink:
self._buildDirectLink(inmesh, outmesh)
# combined inputs
if self.combinputs > 0:
cin = LinearLayer(self.combinputs, name='globalin')
self.addInputModule(cin)
if 'globalinconn' not in self.predefined:
self.predefined['globalinconn'] = MotherConnection(
cin.componentOutdim * hiddenmesh.componentIndim,
'globalinconn')
self._linkToAll(cin, hiddenmesh, self.predefined['globalinconn'])
def buildNestedNetwork():
""" build a nested network. """
N = FeedForwardNetwork('outer')
a = LinearLayer(1, name='a')
b = LinearLayer(2, name='b')
c = buildNetwork(2, 3, 1)
c.name = 'inner'
N.addInputModule(a)
N.addModule(c)
N.addOutputModule(b)
N.addConnection(FullConnection(a, b))
N.addConnection(FullConnection(b, c))
N.sortModules()
return N
def buildMixedNestedNetwork():
""" build a nested network with the inner one being a ffn and the outer one being recurrent. """
N = RecurrentNetwork('outer')
a = LinearLayer(1, name='a')
b = LinearLayer(2, name='b')
c = buildNetwork(2, 3, 1)
c.name = 'inner'
N.addInputModule(a)
N.addModule(c)
N.addOutputModule(b)
N.addConnection(FullConnection(a, b))
N.addConnection(FullConnection(b, c))
N.addRecurrentConnection(FullConnection(c, c))
N.sortModules()
return N
def buildSimpleLSTMNetwork(peepholes=False):
N = RecurrentNetwork('simpleLstmNet')
i = LinearLayer(1, name='i')
h = LSTMLayer(1, peepholes=peepholes, name='lstm')
o = LinearLayer(1, name='o')
b = BiasUnit('bias')
N.addModule(b)
N.addOutputModule(o)
N.addInputModule(i)
N.addModule(h)
N.addConnection(FullConnection(i, h, name='f1'))
N.addConnection(FullConnection(b, h, name='f2'))
N.addRecurrentConnection(FullConnection(h, h, name='r1'))
N.addConnection(FullConnection(h, o, name='r1'))
N.sortModules()
return N
def buildSimpleMDLSTMNetwork(peepholes = False):
N = RecurrentNetwork('simpleMDLstmNet')
i = LinearLayer(1, name = 'i')
dim = 1
h = MDLSTMLayer(dim, peepholes = peepholes, name = 'MDlstm')
o = LinearLayer(1, name = 'o')
b = BiasUnit('bias')
N.addModule(b)
N.addOutputModule(o)
N.addInputModule(i)
N.addModule(h)
N.addConnection(FullConnection(i, h, outSliceTo = 4*dim, name = 'f1'))
N.addConnection(FullConnection(b, h, outSliceTo = 4*dim, name = 'f2'))
N.addRecurrentConnection(FullConnection(h, h, inSliceTo = dim, outSliceTo = 4*dim, name = 'r1'))
N.addRecurrentConnection(IdentityConnection(h, h, inSliceFrom = dim, outSliceFrom = 4*dim, name = 'rstate'))
N.addConnection(FullConnection(h, o, inSliceTo = dim, name = 'f3'))
N.sortModules()
return N
def buildCyclicNetwork(recurrent):
""" build a cyclic network with 4 modules
:key recurrent: make one of the connections recurrent """
Network = RecurrentNetwork if recurrent else FeedForwardNetwork
N = Network('cyc')
a = LinearLayer(1, name='a')
b = LinearLayer(2, name='b')
c = LinearLayer(3, name='c')
d = LinearLayer(4, name='d')
N.addInputModule(a)
N.addModule(b)
N.addModule(d)
N.addOutputModule(c)
N.addConnection(FullConnection(a, b))
N.addConnection(FullConnection(b, c))
N.addConnection(FullConnection(c, d))
if recurrent:
N.addRecurrentConnection(FullConnection(d, a))
else:
N.addConnection(FullConnection(d, a))
N.sortModules()
return N
def __init__(self, dims, **args):
""" The one required argument specifies the sizes of each dimension (minimum 2) """
SwipingNetwork.__init__(self, dims=dims, **args)
pdims = product(dims)
# the input is a 2D-mesh (as a view on a flat input layer)
inmod = LinearLayer(self.insize * pdims, name='input')
inmesh = ModuleMesh.viewOnFlatLayer(inmod, dims, 'inmesh')
# the output is a 2D-mesh (as a view on a flat sigmoid output layer)
outmod = self.outcomponentclass(self.outputs * pdims, name='output')
outmesh = ModuleMesh.viewOnFlatLayer(outmod, dims, 'outmesh')
if self.componentclass is MDLSTMLayer:
c = lambda: MDLSTMLayer(self.hsize, 2, self.peepholes).meatSlice()
adims = tuple(list(dims) + [4])
hiddenmesh = ModuleMesh(c, adims, 'hidden', baserename=True)
else:
hiddenmesh = ModuleMesh.constructWithLayers(
self.componentclass, self.hsize,
tuple(list(dims) + [self.swipes]), 'hidden')
self._buildSwipingStructure(inmesh, hiddenmesh, outmesh)
# add the identity connections for the states
for m in self.modules:
if isinstance(m, MDLSTMLayer):
tmp = m.stateSlice()
index = 0
for c in list(self.connections[m]):
if isinstance(c.outmod, MDLSTMLayer):
self.addConnection(
IdentityConnection(
tmp,
c.outmod.stateSlice(),
outSliceFrom=self.hsize * (index),
outSliceTo=self.hsize * (index + 1)))
index += 1
self.sortModules()
from pybrain3 import FeedForwardNetwork, LinearLayer, SigmoidLayer, BiasUnit, FullConnection, RecurrentNetwork, \
TanhLayer
#network = RecurrentNetwork() # nowa siec
network=FeedForwardNetwork();
inLayer = LinearLayer(35) # warstwa wejsciowa
#hiddenLayer = SigmoidLayer(5) # tworze ukryta warstwe
hiddenLayer=TanhLayer(5);
outLayer = LinearLayer(1) # tworze warstwe wyjsciowa
bias = BiasUnit() # inicjalizuje Bias
network.addInputModule(inLayer)
network.addModule(bias)
network.addModule(hiddenLayer)
network.addOutputModule(outLayer)
bias_to_hidden = FullConnection(bias, hiddenLayer) # lacze warstwy
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_out = FullConnection(hiddenLayer, outLayer)
network.addConnection(bias_to_hidden) # dodaje polaczenie do sieci
network.addConnection(in_to_hidden)
network.addConnection(hidden_to_out)
network.sortModules()
def buildSomeModules(number = 4):
res = []
for i in range(number):
res.append(LinearLayer(1, 'l'+str(i)))
return res