def __init__(self, train_data, hyper, n_targets=None, label_targets=None):
"""
------------
train_data: pandas DataFrame
Contains columns for features and for target variables. The names of the target variables ends
with the suffix "_tau"
hyper: dictionary
It contains the hyperparameters necessary to run all the functionalities of the model.
They are the following:
"structure" is a list of integers determining the number of neurons in each hidden layer
"epochs" an integer specifying the maximum number of epochs to run during every training session
"learning_rate" a float giving the learning rate of the gradient descend
"momentum" a float giving the value of the momentum for the algorithm
"batch" a bool. If True the method performs full batch learning, i.e. updates of the weights is done
using all the instances of the training set. Else, normal online method is performed
Other parameters regarding cross validation are explained in the base class
"""
Regression.__init__(self, train_data, hyper, n_targets=n_targets, label_targets=label_targets)
self.N = FeedForwardNetwork()
self.structure = [self.n_feature] + hyper['structure'] + [self.n_target]
self._build_net(self.structure)
self.res_params = [self.N.params[i] for i in range(len(self.N.params))]
self.train_fraction = hyper['train_fraction']
self.seed = hyper['seed']
self.epochs = hyper['epochs']
self.learning_rate = hyper['learning_rate']
self.momentum = hyper['momentum']
self.batch = bool(hyper['batch'])
class BMBPTester:
__fnn = None
fnnname = 'buildBMTrainer.xml'
srctestname = 'tester.xlsx'
def __init__(self, psrctestname='tester.xlsx', pfnnname='buildBMTrainer.xml'):
self.fnnname = pfnnname
self.srctestname = psrctestname
self.__fnn = FeedForwardNetwork()
def test(self):
self.__fnn = NetworkReader.readFrom(self.fnnname)
workbook = xlrd.open_workbook(self.srctestname)
sheet1 = workbook.sheet_by_index(0)
x = np.zeros((sheet1.nrows, sheet1.ncols), dtype=np.float)
for i in range(sheet1.nrows):
for j in range(sheet1.ncols):
x[i][j] = sheet1.cell(i, j).value
stestx = MinMaxScaler()
xtest = stestx.fit_transform(x)
sy = joblib.load('sy.pkl')
print(sy)
values = []
for x1 in xtest:
values.append(sy.inverse_transform(self.__fnn.activate(x1).reshape(-1, 1)))
print(self.__fnn.activate(x1))
print(values)
class MyNet:
def __init__(self, file='config.xml'):
self.net = FeedForwardNetwork()
self.file = file
def constructNet(self, input, hidden, output):
inputLayer = LinearLayer(input)
hiddenLayer = TanhLayer(hidden)
outputLayer = LinearLayer(output)
self.net.addInputModule(inputLayer)
self.net.addModule(hiddenLayer)
self.net.addOutputModule(outputLayer)
conn1 = FullConnection(inputLayer, hiddenLayer)
conn2 = FullConnection(hiddenLayer, outputLayer)
self.net.addConnection(conn1)
self.net.addConnection(conn2)
def setup(self):
self.net.sortModules()
def saveToFile(self, file='config.xml'):
NetworkWriter.writeToFile(self.net, file)
def loadFromFile(self, file='config.xml'):
self.net = NetworkReader.readFrom(file)
class MyNet: def __init__(self, file='config.xml'): self.net = FeedForwardNetwork() self.file = file def constructNet(self, input, hidden, output): inputLayer = LinearLayer(input) hiddenLayer = TanhLayer(hidden) outputLayer = LinearLayer(output) self.net.addInputModule(inputLayer) self.net.addModule(hiddenLayer) self.net.addOutputModule(outputLayer) conn1 = FullConnection(inputLayer, hiddenLayer) conn2 = FullConnection(hiddenLayer, outputLayer) self.net.addConnection(conn1) self.net.addConnection(conn2) def setup(self): self.net.sortModules() def saveToFile(self,file='config.xml'): NetworkWriter.writeToFile(self.net, file) def loadFromFile(self, file='config.xml'): self.net = NetworkReader.readFrom(file)
def __init__(self):
self.Q = FeedForwardNetwork()
# La funcion de valor se representa con una red neuronal
# Input: S = (Angulo, Velocidad angular, Posicion), A = accion
# Output: Valor
# 2 capas ocultas de 5 neuronas cada una
# Funcion de activacion sigmoidea
inLayer = SigmoidLayer(4, name="Input Layer")
hiddenLayer1 = SigmoidLayer(5, name="Hidden Layer 1")
hiddenLayer2 = SigmoidLayer(5, name="Hidden Layer 2")
outLayer = SigmoidLayer(1, name="Output Layer")
self.Q.addInputModule(inLayer)
self.Q.addModule(hiddenLayer1)
self.Q.addModule(hiddenLayer2)
self.Q.addOutputModule(outLayer)
connInToHidden1 = FullConnection(inLayer, hiddenLayer1)
connHidden1ToHidden2 = FullConnection(hiddenLayer1, hiddenLayer2)
connHidden2ToOut = FullConnection(hiddenLayer2, outLayer)
self.Q.addConnection(connInToHidden1)
self.Q.addConnection(connHidden1ToHidden2)
self.Q.addConnection(connHidden2ToOut)
self.Q.sortModules()
def __setUpBrain(self, genome):
"""
Set up PyBrain's neural network
Args:
genome (G1DList): PyEvolve's individual container
"""
self.network = FeedForwardNetwork()
inLayer = TanhLayer(14)
hiddenLayer = TanhLayer(12)
hiddenLayer2 = TanhLayer(6)
outLayer = TanhLayer(2)
self.network.addInputModule(inLayer)
self.network.addModule(hiddenLayer)
self.network.addModule(hiddenLayer2)
self.network.addOutputModule(outLayer)
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_hidden2 = FullConnection(hiddenLayer, hiddenLayer2)
hidden2_to_out = FullConnection(hiddenLayer2, outLayer)
self.network.addConnection(in_to_hidden)
self.network.addConnection(hidden_to_hidden2)
self.network.addConnection(hidden2_to_out)
self.network.sortModules()
new_params = numpy.array(genome.genomeList)
self.network._setParameters(new_params)
def __init__(self, arg):
self.inputsize = arg[0]
self.outputsize = arg[-1]
self.hiden = arg[1:-1]
self.err = 1
self.old_err = 1
b = []
b.append(self.inputsize)
b += self.hiden
b.append(self.outputsize)
#print b#"%s, %s, %s, hiddenclass=TanhLayer"%(self.inputsize, self.hiden, self.outputsize)
self.net = FeedForwardNetwork()
self.inputlayer = LinearLayer(self.inputsize, "Input")
self.net.addInputModule(self.inputlayer)
self.outputlayer = LinearLayer(self.outputsize, "Output")
self.net.addOutputModule(self.outputlayer)
self.hidenlayers = []
for i in xrange(len(self.hiden)):
self.hidenlayers.append(SigmoidLayer(self.hiden[i], "hiden%s" % i))
self.net.addModule(self.hidenlayers[-1])
self.net.addConnection(
FullConnection(self.inputlayer, self.outputlayer))
for i in xrange(len(self.hidenlayers)):
self.net.addConnection(
FullConnection(self.inputlayer, self.hidenlayers[i]))
self.net.addConnection(
FullConnection(self.hidenlayers[i], self.outputlayer))
for i in xrange(len(self.hidenlayers)):
for j in xrange(i + 1, len(self.hidenlayers)):
self.net.addConnection(
FullConnection(self.hidenlayers[i], self.hidenlayers[j]))
#self.print_conections(self.net)
self.net.sortModules()
self.ds = SupervisedDataSet(self.inputsize, self.outputsize)
def Update(self, hiden, h):
self.net = FeedForwardNetwork()
self.inputlayer = LinearLayer(self.inputsize, "Input")
self.net.addInputModule(self.inputlayer)
self.outputlayer = LinearLayer(self.outputsize, "Output")
self.net.addOutputModule(self.outputlayer)
self.hidenlayers = []
for i in xrange(len(hiden)):
self.hidenlayers.append(SigmoidLayer(hiden[i], "hiden%s" % i))
self.net.addModule(self.hidenlayers[-1])
self.net.addConnection(
FullConnection(self.inputlayer, self.outputlayer))
for i in xrange(len(self.hidenlayers)):
self.net.addConnection(
FullConnection(self.inputlayer, self.hidenlayers[i]))
self.net.addConnection(
FullConnection(self.hidenlayers[i], self.outputlayer))
for i in xrange(len(self.hidenlayers)):
for j in xrange(i + 1, len(self.hidenlayers)):
if i < h:
self.net.addConnection(
FullConnection(self.hidenlayers[i],
self.hidenlayers[j]))
elif i == h:
self.net.addConnection(
FullConnection(self.hidenlayers[i],
self.hidenlayers[j],
inSliceTo=hiden[i] - 1))
else:
self.net.addConnection(
FullConnection(self.hidenlayers[i],
self.hidenlayers[j]))
#self.print_conections(self.net)
self.net.sortModules()
self.hiden = hiden
def __init__(self, genes=None):
self.net = FeedForwardNetwork()
inLayer = LinearLayer(Brain.G_INPUTNODES, name='input')
hiddenLayer1 = SigmoidLayer(Brain.G_HIDDENNODES_L1, name='hidden1')
hiddenLayer2 = SigmoidLayer(Brain.G_HIDDENNODES_L2, name='hidden2')
outLayer = SigmoidLayer(Brain.G_OUTPUTNODES, name='out')
bias = BiasUnit(name='bias')
self.net.addInputModule(inLayer)
self.net.addModule(hiddenLayer1)
self.net.addModule(hiddenLayer2)
self.net.addModule(bias)
self.net.addOutputModule(outLayer)
in_to_hidden1 = FullConnection(inLayer, hiddenLayer1)
hidden1_to_hidden2 = FullConnection(hiddenLayer1, hiddenLayer2)
hidden2_to_out = FullConnection(hiddenLayer2, outLayer)
bias_to_hidden1 = FullConnection(bias, hiddenLayer1)
bias_to_hidden2 = FullConnection(bias, hiddenLayer2)
bias_to_out = FullConnection(bias, outLayer)
self.net.addConnection(in_to_hidden1)
self.net.addConnection(hidden1_to_hidden2)
self.net.addConnection(hidden2_to_out)
self.net.addConnection(bias_to_hidden1)
self.net.addConnection(bias_to_hidden2)
self.net.addConnection(bias_to_out)
self.net.sortModules()
if genes != None:
self.import_genes(genes)
def __init__(self, genes=None):
self.net = FeedForwardNetwork()
self.inLayer = TanhLayer(16)
self.hiddenLayer = TanhLayer(20)
self.hiddenLayer2 = TanhLayer(20)
self.outLayer = SoftmaxLayer(4)
self.net.addInputModule(self.inLayer)
self.net.addModule(self.hiddenLayer)
self.net.addModule(self.hiddenLayer2)
self.net.addOutputModule(self.outLayer)
self.in_to_hidden = FullConnection(self.inLayer, self.hiddenLayer)
self.hidden1_to_hidden2 = FullConnection(self.hiddenLayer, self.hiddenLayer2)
self.hidden2_to_out = FullConnection(self.hiddenLayer2, self.outLayer)
self.net.addConnection(self.in_to_hidden)
self.net.addConnection(self.hidden1_to_hidden2)
self.net.addConnection(self.hidden2_to_out)
self.net.sortModules()
# Set the params to the provided params
if genes is not None:
self.net._setParameters(genes)
def __init__(self, network, camada_entrada, camada_oculta, camada_saida):
self.network = network
self.network = FeedForwardNetwork()
self.camada_entrada = camada_entrada
self.camada_oculta = camada_oculta
self.camada_saida = camada_saida
self.ligacao_entrada_oculta = None
self.ligacao_oculta_saida = None
self.defineArquitetura()
def main(f_samples):
f_reading = open(f_samples, 'r')
global data
data = []
for line in f_reading:
line = line.split()
data.append( (float(line[0]), float(line[-1])) )
#function
data_module = lambda x: map( lambda z: data[z], filter( lambda y: y% 5 == x, xrange(len(data)) ) )
global data1
data1 = [data_module(0), data_module(1), data_module(2), data_module(3), data_module(4)]
global data_transformed
data_transformed = take(data, rate = 60)
global data_transformed_training
data_transformed_training = map( lambda x: data_transformed[x], filter( lambda x: uniform(0, 1) > 0.3, xrange(len(data_transformed)) ))
#Learning process-----------------------------------------------------------------
global net, samples, trainer
net = FeedForwardNetwork()
inLayer = LinearLayer(3)
hiddenLayer0 = SigmoidLayer(1)
hiddenLayer1 = SigmoidLayer(3)
outLayer = LinearLayer(1)
net.addInputModule(inLayer)
# net.addModule(hiddenLayer0)
# net.addModule(hiddenLayer1)
net.addOutputModule(outLayer)
# net.addConnection(FullConnection(inLayer, hiddenLayer0))
net.addConnection(FullConnection(inLayer, outLayer))
# net.addConnection(FullConnection(hiddenLayer0, outLayer))
# net.addConnection(FullConnection(hiddenLayer0, hiddenLayer1))
# net.addConnection(FullConnection(hiddenLayer1, outLayer))
net.sortModules()
print net
##Net with 3 inputs, 8 hidden neurons in a layerand 8 in another, and 1 out.
#net = buildNetwork(3,8,8,1)
##Set with 2 inputs and one output for each sample
samples = SupervisedDataSet(3,1)
for i in data_transformed_training:
samples.addSample(i['past'], i['next'] - i['average'])
trainer = BackpropTrainer(net, samples)
print 'Training'
trainer.trainUntilConvergence(maxEpochs= 10)
print 'Comparing'
compare_net_samples(net, data_transformed)
print "Number of samples %d for training." %len(data_transformed_training)
def __init__(self, x, y, direction):
self.age = 0
# position
self.x = x
self.y = y
# number of fruits peeled
self.num_peeled = 0
self.num_eaten = 0
self.num_moved = 0
# orientation (0 - 359 degrees)
self.direction = direction
# touching anything
self.touching = None
self.sees = None
# hunger sensor
self.hunger = 2000
self.avg_hunger = 0
###
# Neural Network
#
# Inputs:
# 1. sees_peeled_orange
# 2. sees_unpeeled_orange
# 3. sees_peeled_banana
# 4. sees_unpeeled_banana
# 5. sees_animat
# 6. sees_wall
# 7. hunger
# 8. touching_peeled_orange
# 9. touching_unpeeled_orange
# 10. touching_peeled_banana
# 11. touching_unpeeled_banana
# 12. touching_animat
# 13. touching_wall
###
self.net = FeedForwardNetwork()
self.net.addInputModule(LinearLayer(13, name='in'))
self.net.addModule(SigmoidLayer(14, name='hidden'))
self.net.addOutputModule(LinearLayer(5, name='out'))
self.net.addConnection(
FullConnection(self.net['in'], self.net['hidden']))
self.net.addConnection(
FullConnection(self.net['hidden'], self.net['out']))
self.net.sortModules()
# thresholds for deciding an action
self.move_threshold = 0
self.peel_threshold = 0
self.eat_threshold = 0
def __init__(self, hidden_neuron_num=1, hidden_type='sigmoid'):
self.hidden_neuron_num = hidden_neuron_num
self.hidden_type = hidden_type
self.net = FeedForwardNetwork()
self.samples = SupervisedDataSet(784, 784)
self.vectorizer = ImageVectorizer()
self.add_layers()
self.add_connections()
self.sort()
def initMaxentNetwork(): """Builds a network with just a sigmoid output layer, i.e. a multi-class maximum entropy model.""" fnn = FeedForwardNetwork() inLayer = LinearLayer(numFeatures) fnn.addInputModule(inLayer) outLayer = SigmoidLayer(3) fnn.addOutputModule(outLayer) fnn.addConnection(FullConnection(inLayer, outLayer)) fnn.sortModules() return fnn
def __init__(self, hidden_layers, ally_champ_obj_list,
enemy_champ_obj_list):
self.ally_champ_obj_list = ally_champ_obj_list
self.enemy_champ_obj_list = enemy_champ_obj_list
self.set_nodes()
self.network = FeedForwardNetwork()
connect_queue = Queue.Queue()
for layer in xrange(0, hidden_layers):
connect_queue.put(
TanhLayer(self.input_node_count,
name='hidden_layer_{}'.format(layer)))
connect_queue.put(SigmoidLayer(1, name='output_layer'))
prev_layer = LinearLayer(self.input_node_count, name='input_layer')
self.network.addInputModule(prev_layer)
while not connect_queue.empty():
current_layer = connect_queue.get()
if current_layer.name == 'output_layer':
self.network.addOutputModule(current_layer)
else:
self.network.addModule(current_layer)
bias = BiasUnit()
bias_connection = FullConnection(
bias,
current_layer,
name="bias_to_{}_connection".format(current_layer.name))
self.network.addModule(bias)
self.network.addConnection(bias_connection)
connection = FullConnection(prev_layer,
current_layer,
name="{}_to_{}_connection".format(
prev_layer.name,
current_layer.name))
self.network.addConnection(connection)
prev_layer = current_layer
self.network.sortModules()
def __init__(self, x, y, direction): self.age = 0 # position self.x = x self.y = y # number of going back and forth for different foods self.backForth = 0 self.LastFood = None # the last food animat ate # orientation (0 - 359 degrees) self.direction = direction # carrying food self.food = None # touching anything self.touching = None self.sees = None # hunger sensor self.fruit_hunger = 2000 self.veggie_hunger = 2000 self.avg_fruit_hunger = 0 self.avg_veggie_hunger = 0 # neural net self.net = FeedForwardNetwork() self.net.addInputModule(LinearLayer(12, name='in')) self.net.addModule(SigmoidLayer(13, name='hidden')) self.net.addOutputModule(LinearLayer(6, name='out')) self.net.addConnection(FullConnection(self.net['in'], self.net['hidden'])) self.net.addConnection(FullConnection(self.net['hidden'], self.net['out'])) self.net.sortModules() # thresholds for deciding an action self.move_threshold = 0 self.pickup_threshold = 0 self.putdown_threshold = 0 self.eat_threshold = 0
def __init__(self, input_size, output_size, number_of_layers=3, size_of_hidden_layers=3, type_of_hidden_layer='sigmoid', net_bias=False, epochs=100):
self.net = FeedForwardNetwork()
self.num_epochs = epochs
# set up layers of the network
layers = []
for i in range(number_of_layers):
if i == 0:
layers.append(LinearLayer(input_size))
self.net.addInputModule(layers[i])
elif i == (number_of_layers-1):
layers.append(LinearLayer(output_size))
self.net.addOutputModule(layers[i])
self.net.addConnection(FullConnection(layers[i-1], layers[i]))
else:
if type_of_hidden_layer == 'linear':
layers.append(LinearLayer((input_size + output_size) / 2))
elif type_of_hidden_layer == 'sigmoid':
layers.append(SigmoidLayer((input_size + output_size) / 2))
elif type_of_hidden_layer == 'tanh':
layers.append(TanhLayer((input_size + output_size) / 2))
self.net.addModule(layers[i])
self.net.addConnection(FullConnection(layers[i-1], layers[i]))
self.net.sortModules()
self.input_size = input_size
self.output_size = output_size
def buildNonGravityNet(recurrent=False):
if recurrent:
net = RecurrentNetwork()
else:
net = FeedForwardNetwork()
l1 = LinearLayer(2)
l2 = LinearLayer(3)
s1 = SigmoidLayer(2)
l3 = LinearLayer(1)
net.addInputModule(l1)
net.addModule(l2)
net.addModule(s1)
net.addOutputModule(l3)
net.addConnection(IdentityConnection(l1, l2, outSliceFrom=1))
net.addConnection(IdentityConnection(l1, l2, outSliceTo=2))
net.addConnection(IdentityConnection(l2, l3, inSliceFrom=2))
net.addConnection(IdentityConnection(l2, l3, inSliceTo=1))
net.addConnection(IdentityConnection(l1, s1))
net.addConnection(IdentityConnection(l2, s1, inSliceFrom=1))
net.addConnection(IdentityConnection(s1, l3, inSliceFrom=1))
if recurrent:
net.addRecurrentConnection(IdentityConnection(s1, l1))
net.addRecurrentConnection(
IdentityConnection(l2, l2, inSliceFrom=1, outSliceTo=2))
net.sortModules()
return net
def __init__(self, hidden_layers, data_index_size):
self.network = FeedForwardNetwork()
connect_queue = Queue.Queue()
for layer in xrange(0, hidden_layers):
connect_queue.put(TanhLayer(data_index_size, name = 'hidden_layer_{}'.format(layer)))
connect_queue.put(SigmoidLayer(1, name = 'output_layer'))
prev_layer = LinearLayer(data_index_size, name = 'input_layer')
self.network.addInputModule(prev_layer)
while not connect_queue.empty():
print 'layer'
current_layer = connect_queue.get()
if current_layer.name == 'output_layer':
self.network.addOutputModule(current_layer)
else:
self.network.addModule(current_layer)
bias = BiasUnit()
bias_connection = FullConnection(bias, current_layer, name = "bias_to_{}_connection".format(current_layer.name))
self.network.addModule(bias)
self.network.addConnection(bias_connection)
connection = FullConnection(prev_layer, current_layer, name = "{}_to_{}_connection".format(prev_layer.name, current_layer.name))
self.network.addConnection(connection)
prev_layer = current_layer
print 'sorting....'
self.network.sortModules()
def __init__(self, genes=None): self.net = FeedForwardNetwork() inLayer = LinearLayer(Brain.G_INPUTNODES, name='input') hiddenLayer1 = SigmoidLayer(Brain.G_HIDDENNODES_L1, name='hidden1') hiddenLayer2 = SigmoidLayer(Brain.G_HIDDENNODES_L2, name='hidden2') outLayer = SigmoidLayer(Brain.G_OUTPUTNODES, name='out') bias = BiasUnit(name='bias') self.net.addInputModule(inLayer) self.net.addModule(hiddenLayer1) self.net.addModule(hiddenLayer2) self.net.addModule(bias) self.net.addOutputModule(outLayer) in_to_hidden1 = FullConnection(inLayer, hiddenLayer1) hidden1_to_hidden2 = FullConnection(hiddenLayer1, hiddenLayer2) hidden2_to_out = FullConnection(hiddenLayer2, outLayer) bias_to_hidden1 = FullConnection(bias, hiddenLayer1) bias_to_hidden2 = FullConnection(bias, hiddenLayer2) bias_to_out = FullConnection(bias, outLayer) self.net.addConnection(in_to_hidden1) self.net.addConnection(hidden1_to_hidden2) self.net.addConnection(hidden2_to_out) self.net.addConnection(bias_to_hidden1) self.net.addConnection(bias_to_hidden2) self.net.addConnection(bias_to_out) self.net.sortModules() if genes != None: self.import_genes(genes)
def __init__(self, grid_size, hidden_list):
"""Sets up the neural network.
@param grid_size: the size of the grid, for specifying the input layer.
@param hidden_list: a list containing the number of nodes in each hidden layer.
"""
self.net = FeedForwardNetwork()
in_layer = LinearLayer(grid_size*grid_size)
self.net.addInputModule(in_layer)
out_layer = LinearLayer(4)
self.net.addOutputModule(out_layer)
hidden_layers = []
for i in hidden_list:
hidden_layer = SigmoidLayer(i)
hidden_layers.append(hidden_layer)
self.net.addModule(hidden_layer)
self.net.addConnection(FullConnection(in_layer, hidden_layers[0]))
if len(hidden_layers) > 1:
for i in range(1, len(hidden_layers) - 1):
self.net.addConnection(FullConnection(hidden_layers[i], hidden_layers[i+1]))
self.net.addConnection(FullConnection(hidden_layers[-1], out_layer))
self.net.sortModules()
def PrepareModel(self, savedmodel = None): if savedmodel != None: self.trainer = savedmodel else: attributescount=len(self.traindata[0]) self.ds = SupervisedDataSet(attributescount, 1) for i in range(len(self.traindata)): self.ds.appendLinked(self.traindata[i], self.trainlabel[i]) self.net = FeedForwardNetwork() inLayer = LinearLayer(len(self.traindata[0])) self.net.addInputModule(inLayer) hiddenLayers=[] for i in range(self.hiddenlayerscount): hiddenLayer=SigmoidLayer(self.hiddenlayernodescount) hiddenLayers.append(hiddenLayer) self.net.addModule(hiddenLayer) outLayer = LinearLayer(1) self.net.addOutputModule(outLayer) layers_connections=[] layers_connections.append(FullConnection(inLayer, hiddenLayers[0])) for i in range(self.hiddenlayerscount-1): layers_connections.append(FullConnection(hiddenLayers[i-1], hiddenLayers[i])) layers_connections.append(FullConnection(hiddenLayers[-1], outLayer)) for layers_connection in layers_connections: self.net.addConnection(layers_connection) self.net.sortModules() #training the self.network self.trainer = BackpropTrainer(self.net, self.ds) self.trainer.train()
def __init__(self, num_input, num_hidden, num_output):
# self.net = buildNetwork(num_input, num_hidden, num_output, bias = True)
self.net = FeedForwardNetwork()
self.num_input = num_input
self.num_hidden = num_hidden
self.num_output = num_output
inLayer = LinearLayer(num_input, name='in')
hiddenLayer1 = SigmoidLayer(num_hidden, name='hidden1')
outLayer = LinearLayer(num_output, name='out')
self.net.addInputModule(inLayer)
self.net.addModule(hiddenLayer1)
self.net.addOutputModule(outLayer)
self.in_to_hidden = FullConnection(inLayer, hiddenLayer1)
self.hidden_to_out = FullConnection(hiddenLayer1, outLayer)
self.net.addConnection(self.in_to_hidden)
self.net.addConnection(self.hidden_to_out)
self.net.sortModules()
self.dataset = None
def build_fnn():
fnn = FeedForwardNetwork()
inLayer = LinearLayer(2)
hiddenLayer = TanhLayer(50)
outLayer = SoftmaxLayer(2)
fnn.addInputModule(inLayer)
fnn.addModule(hiddenLayer)
fnn.addOutputModule(outLayer)
return fnn
def _new_1h_net(window):
net = FeedForwardNetwork()
inl = SigmoidLayer(window*window*2+1)
hidden1 = SigmoidLayer(window*window*2)
outl = SigmoidLayer(1)
net.addInputModule(inl)
net.addModule(hidden1)
net.addOutputModule(outl)
c1 = FullConnection(inl, hidden1)
c2 = FullConnection(hidden1, outl)
net.addConnection(c1)
net.addConnection(c2)
return net
def PrepareModel(self, savedmodel=None):
if savedmodel != None:
self.trainer = savedmodel
else:
attributescount = len(self.traindata[0])
nrclass = len(set(self.trainlabel))
self.ds = ClassificationDataSet(attributescount,
target=nrclass,
nb_classes=nrclass,
class_labels=list(
set(self.trainlabel)))
for i in range(len(self.traindata)):
self.ds.appendLinked(self.traindata[i], [self.trainlabel[i]])
self.ds._convertToOneOfMany()
self.net = FeedForwardNetwork()
inLayer = LinearLayer(len(self.traindata[0]))
self.net.addInputModule(inLayer)
hiddenLayers = []
for i in range(self.hiddenlayerscount):
hiddenLayer = SigmoidLayer(self.hiddenlayernodescount)
hiddenLayers.append(hiddenLayer)
self.net.addModule(hiddenLayer)
outLayer = SoftmaxLayer(nrclass)
self.net.addOutputModule(outLayer)
layers_connections = []
layers_connections.append(FullConnection(inLayer, hiddenLayers[0]))
for i in range(self.hiddenlayerscount - 1):
layers_connections.append(
FullConnection(hiddenLayers[i - 1], hiddenLayers[i]))
layers_connections.append(
FullConnection(hiddenLayers[-1], outLayer))
for layers_connection in layers_connections:
self.net.addConnection(layers_connection)
self.net.sortModules()
#training the network
self.trainer = BackpropTrainer(self.net, self.ds)
self.trainer.train()
def __init__(self, inputsize, outputsize, hiden=[1]):
self.inputsize = inputsize
self.outputsize = outputsize
self.hiden = hiden
self.err = 1
self.old_err = 1
#print type(self.hiden)
if type(self.hiden) == str:
#print "type str"
self.hiden = self.hiden[1:-1]
b = self.hiden.split(", ")
c = []
for i in b:
c.append(int(i))
self.hiden = c[:]
b = []
b.append(self.inputsize)
b += self.hiden
b.append(self.outputsize)
#print b#"%s, %s, %s, hiddenclass=TanhLayer"%(self.inputsize, self.hiden, self.outputsize)
self.net = FeedForwardNetwork()
self.inputlayer = LinearLayer(self.inputsize, "Input")
self.net.addInputModule(self.inputlayer)
self.outputlayer = LinearLayer(self.outputsize, "Output")
self.net.addOutputModule(self.outputlayer)
self.hidenlayers = []
for i in xrange(len(self.hiden)):
self.hidenlayers.append(SigmoidLayer(self.hiden[i], "hiden%s" % i))
self.net.addModule(self.hidenlayers[-1])
self.net.addConnection(
FullConnection(self.inputlayer, self.outputlayer))
for i in xrange(len(self.hidenlayers)):
self.net.addConnection(
FullConnection(self.inputlayer, self.hidenlayers[i]))
self.net.addConnection(
FullConnection(self.hidenlayers[i], self.outputlayer))
for i in xrange(len(self.hidenlayers)):
for j in xrange(i + 1, len(self.hidenlayers)):
self.net.addConnection(
FullConnection(self.hidenlayers[i], self.hidenlayers[j]))
#self.print_conections(self.net)
self.net.sortModules()
self.ds = SupervisedDataSet(self.inputsize, self.outputsize)
def initNetwork(self):
#Intiailize Neural Nets
self.neuralNet = FeedForwardNetwork()
#Define and add each set of layers
inLayer = LinearLayer(5)
hiddenLayer = SigmoidLayer(15)
outLayer = LinearLayer(5)
self.neuralNet.addInputModule(inLayer)
self.neuralNet.addModule(hiddenLayer)
self.neuralNet.addOutputModule(outLayer)
#Create conenctions
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_out = FullConnection(hiddenLayer, outLayer)
self.neuralNet.addConnection(in_to_hidden)
self.neuralNet.addConnection(hidden_to_out)
#Sort the NeuralNet
self.neuralNet.sortModules()
#Add supervised data sets
ds = SupervisedDataSet(NNInitializer.NUMBER_OF_INPUTS,
NNInitializer.NUMBER_OF_OUTPUTS)
inputSet, outputSet = self.loadTrainingSet('scents_based_input',
'scents_based_output')
#inputSet, outputSet = self.generateTrainingSet()
print "Adding samples to data set...."
for i, val in enumerate(inputSet):
# print "Input Set: "
# print inputSet[i]
# print "Output Set: "
# print outputSet[i]
ds.addSample(inputSet[i], outputSet[i])
print "Done."
print "Starting training...."
#Perform Training
trainer = BackpropTrainer(self.neuralNet, ds)
trainer.train()
print "Done."
def __init__(self, n_in, n_hidden, n_out):
self.net = FeedForwardNetwork()
inLayer = LinearLayer(n_in)
hiddenLayer1 = SigmoidLayer(n_hidden)
hiddenLayer2 = SigmoidLayer(n_hidden)
outLayer = LinearLayer(n_out)
self.net.addInputModule(inLayer)
self.net.addModule(hiddenLayer1)
self.net.addModule(hiddenLayer2)
self.net.addOutputModule(outLayer)
in_to_hidden = FullConnection(inLayer, hiddenLayer1)
hidden_to_out = FullConnection(hiddenLayer2, outLayer)
hidden_to_hidden = FullConnection(hiddenLayer1, hiddenLayer2)
self.net.addConnection(in_to_hidden)
self.net.addConnection(hidden_to_hidden)
self.net.addConnection(hidden_to_out)
self.net.sortModules()
#self.net.params
self.ds = SupervisedDataSet(n_in, n_out)
def __init__(self, hidden_layers, data_index_size):
self.network = FeedForwardNetwork()
connect_queue = Queue.Queue()
for layer in xrange(0, hidden_layers):
connect_queue.put(
TanhLayer(data_index_size,
name='hidden_layer_{}'.format(layer)))
connect_queue.put(SigmoidLayer(1, name='output_layer'))
prev_layer = LinearLayer(data_index_size, name='input_layer')
self.network.addInputModule(prev_layer)
while not connect_queue.empty():
print 'layer'
current_layer = connect_queue.get()
if current_layer.name == 'output_layer':
self.network.addOutputModule(current_layer)
else:
self.network.addModule(current_layer)
bias = BiasUnit()
bias_connection = FullConnection(
bias,
current_layer,
name="bias_to_{}_connection".format(current_layer.name))
self.network.addModule(bias)
self.network.addConnection(bias_connection)
connection = FullConnection(prev_layer,
current_layer,
name="{}_to_{}_connection".format(
prev_layer.name,
current_layer.name))
self.network.addConnection(connection)
prev_layer = current_layer
print 'sorting....'
self.network.sortModules()
def simple_network(data, digit, train_ds, test_ds):
# n = buildNetwork(train_ds.indim, 1, train_ds.outdim, outclass=SoftmaxLayer)
n = FeedForwardNetwork()
inLayer = LinearLayer(64)
outLayer = SoftmaxLayer(10)
n.addInputModule(inLayer)
n.addOutputModule(outLayer)
n.addConnection(FullConnection(inLayer, outLayer))
n.sortModules()
trainer = BackpropTrainer(n, dataset=train_ds, momentum=0.1, verbose=True,
weightdecay=0.01)
trainer.trainUntilConvergence(maxEpochs=25)
result = percentError(trainer.testOnClassData(dataset=test_ds),
test_ds['class'])
# result = validate(trainer, train_ds, 5, 10)
print 'Simple network - Percent Error', result
return result
def __init__(self, num_features, num_hidden_neurons): super(NNet,self).__init__(num_features) self.ds = SupervisedDataSet(num_features, 1) self.net = FeedForwardNetwork() self.net.addInputModule(LinearLayer(num_features, name='in')) self.net.addModule(LinearLayer(num_hidden_neurons, name='hidden')) self.net.addOutputModule(LinearLayer(1, name='out')) self.net.addConnection(FullConnection(self.net['in'], self.net['hidden'], name='c1')) self.net.addConnection(FullConnection(self.net['hidden'], self.net['out'], name='c2')) self.net.sortModules()
def train(self):
n = FeedForwardNetwork()
dataModel = SongFactory(self.major).getModels()
ds = SupervisedDataSet(static.NUM_OF_INPUTS, 1)
#adds samples from the data received from songfactory and the k
for data in dataModel:
for input, target in data.model:
print input, target
ds.addSample(input, target)
#instantiate the network
self.net = FeedForwardNetwork()
bias = BiasUnit()
self.net.addModule(bias)
#create the layers of the network
inLayer = LinearLayer(static.NUM_OF_INPUTS)
outLayer = LinearLayer(1)
hidden1 = SigmoidLayer(25)
hidden2 = SigmoidLayer(5)
#add the layers
self.net.addInputModule(inLayer)
self.net.addOutputModule(outLayer)
self.net.addModule(hidden1)
self.net.addModule(hidden2)
#create the connection
in_h1 = FullConnection(inLayer,hidden1)
h1_h2 = FullConnection(hidden1, hidden2)
h2_out = FullConnection(hidden2, outLayer)
b_h1 = FullConnection(bias, hidden1)
b_h2 = FullConnection(bias, hidden2)
#add the connection
self.net.addConnection(in_h1)
self.net.addConnection(h1_h2)
self.net.addConnection(h2_out)
self.net.addConnection(b_h1)
self.net.addConnection(b_h2)
self.net.sortModules()
#trainer to edit the network
trainer = BackpropTrainer(self.net, ds, learningrate = 0.003)
trainer.trainEpochs(25)
def create_network(self, nFeatures, hidden1Size=20, nClasses=1):
# create network object
self.ffn = FeedForwardNetwork()
# create layer objects
inLayer = LinearLayer(nFeatures, name="input")
hiddenLayer = SigmoidLayer(hidden1Size, name="hidden1")
#hiddenLayer2 = SigmoidLayer(hidden2Size, name="hidden2")
outLayer = LinearLayer(nClasses, name="output")
# add layers to feed forward network
self.ffn.addInputModule(inLayer)
self.ffn.addModule(hiddenLayer)
#self.ffn.addModule(hiddenLayer2)
self.ffn.addOutputModule(outLayer)
# add bias unit to layers
self.ffn.addModule(BiasUnit(name='bias'))
# establish connections between layers
self.in_to_hidden = FullConnection(inLayer, hiddenLayer)
#hidden_to_hidden = FullConnection(hiddenLayer, hiddenLayer2)
self.hidden_to_out = FullConnection(hiddenLayer, outLayer)
# print "into hidden: {}".format(len(in_to_hidden.params))
# print "into out: {}".format(len(hidden_to_out.params))
# add connections to network
self.ffn.addConnection(self.in_to_hidden)
#self.ffn.addConnection(hidden_to_hidden)
self.ffn.addConnection(self.hidden_to_out)
# necessary, sort layers into correct/certain order
self.ffn.sortModules()
# dataset object
self.train_ds = SupervisedDataSet(nFeatures, nClasses)
self.validate_ds = SupervisedDataSet(nFeatures, nClasses)
def set_network(self, in_count, hidden_counts, out_count):
assert len(hidden_counts) > 0
self.in_count = in_count
self.out_count = out_count
self.net = FeedForwardNetwork()
in_layer = LinearLayer(in_count)
hidden_layers = [SigmoidLayer(count) for count in hidden_counts]
out_layer = SigmoidLayer(out_count)
self.net.addInputModule(in_layer)
for layer in hidden_layers:
self.net.addModule(layer)
self.net.addOutputModule(out_layer)
in_connection = FullConnection(in_layer, hidden_layers[0])
hidden_connections = [
FullConnection(layer1, layer2)
for layer1, layer2 in zip(hidden_layers[0:-1], hidden_layers[1:])
]
out_connection = FullConnection(hidden_layers[-1], out_layer)
self.net.addConnection(in_connection)
for connection in hidden_connections:
self.net.addConnection(connection)
self.net.addConnection(out_connection)
self.net.sortModules()
def narcolepsy(self, naps, awakenings, obesity):
parameters = [naps, awakenings, obesity]
# Init network
network = FeedForwardNetwork()
# Init Layers
inLayer = LinearLayer(3)
outLayer = LinearLayer(1)
# Init connection
in_to_out = FullConnection(inLayer, outLayer)
# Add modules
network.addInputModule(inLayer)
network.addInputModule(outLayer)
# Add connections
network.addConnection(in_to_out)
# Sort
network.sortModules()
# Set equal weights
# TODO: Use learning to learn weights over time
# in_to_out._setParameters([.1,.1,.1])
probability = network.activate(parameters)[0]
return probability
def __init__(self, alpha):
self.name = "ANNApprox"
self.network = FeedForwardNetwork()
inLayer = LinearLayer(4)
hiddenLayer = SigmoidLayer(12)
outLayer = LinearLayer(1)
self.network.addInputModule(inLayer)
self.network.addModule(hiddenLayer)
self.network.addOutputModule(outLayer)
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_out = FullConnection(hiddenLayer, outLayer)
self.network.addConnection(in_to_hidden)
self.network.addConnection(hidden_to_out)
# Last step to make sure everything works in the connections
self.network.sortModules()
self.dataset = SupervisedDataSet(4, 1)
self.trainer = BackpropTrainer(self.network,
self.dataset,
learningrate=alpha,
momentum=0.0,
verbose=True)
def insomnia(self, falling_asleep, awakenings, cant_fall_back, low_sleep_hours):
parameters = [falling_asleep, waking_up, cant_fall_back, low_sleep_hours]
# Init network
network = FeedForwardNetwork()
# Init Layers
inLayer = LinearLayer(4)
outLayer = LinearLayer(1)
# Init connection
in_to_out = FullConnection(inLayer, outLayer)
# Add modules
network.addInputModule(inLayer)
network.addInputModule(outLayer)
# Add connections
network.addConnection(in_to_out)
# Sort
network.sortModules()
# Set equal weights
# TODO: Use learning to learn weights over time
# in_to_out._setParameters([.1,.1,.1,.1])
probability = network.activate(parameters)[0]
return probability
def __init__(self, input_path, output_path):
self.n = FeedForwardNetwork()
self.pix_size = 50
self.input_value = utils.getImages(utils.readLines(input_path))
self.output_value = utils.readLines(output_path)
self.inputUnits = self.pix_size * self.pix_size
self.nbHiddenLayers = 1
self.hiddenUnits = 500
self.outputUnits = len(results)
self.ds = SupervisedDataSet(
self.pix_size * self.pix_size, len(results))
self.initializeDataSet()
self.initilizeNetwork()
self.trainingOnDataSet()
def PrepareModel(self, savedmodel=None):
if savedmodel != None:
self.trainer = savedmodel
else:
attributescount = len(self.traindata[0])
self.ds = SupervisedDataSet(attributescount, 1)
for i in range(len(self.traindata)):
self.ds.appendLinked(self.traindata[i], self.trainlabel[i])
self.net = FeedForwardNetwork()
inLayer = LinearLayer(len(self.traindata[0]))
self.net.addInputModule(inLayer)
hiddenLayers = []
for i in range(self.hiddenlayerscount):
hiddenLayer = SigmoidLayer(self.hiddenlayernodescount)
hiddenLayers.append(hiddenLayer)
self.net.addModule(hiddenLayer)
outLayer = LinearLayer(1)
self.net.addOutputModule(outLayer)
layers_connections = []
layers_connections.append(FullConnection(inLayer, hiddenLayers[0]))
for i in range(self.hiddenlayerscount - 1):
layers_connections.append(
FullConnection(hiddenLayers[i - 1], hiddenLayers[i]))
layers_connections.append(
FullConnection(hiddenLayers[-1], outLayer))
for layers_connection in layers_connections:
self.net.addConnection(layers_connection)
self.net.sortModules()
#training the self.network
self.trainer = BackpropTrainer(self.net, self.ds)
self.trainer.train()
def fit(self, X, y):
self.n = FeedForwardNetwork()
self.n.addInputModule(SigmoidLayer(self.inp_neu, name='in'))
self.n.addModule(SigmoidLayer(self.hid_neu, name='hidden'))
self.n.addOutputModule(LinearLayer(self.out_neu, name='out'))
self.n.addConnection(FullConnection(self.n['in'], self.n['hidden'], name='c1'))
self.n.addConnection(FullConnection(self.n['hidden'], self.n['out'], name='c2'))
self.n.sortModules() #initialisation
self.tstdata, trndata = self.data(X,y).splitWithProportion(self.split_prop)
trainer = BackpropTrainer(self.n, trndata, learningrate=self.learn_rate, momentum=self.nomentum, weightdecay=self.weight_dec)
trainer.trainUntilConvergence(verbose=True, maxEpochs=self.epochs)
return self
def __init__(self,layer_type): self.inputLayer = LinearLayer(2) self.hiddenLayer = layer_type(10) self.outputLayer = layer_type(2) self.net = FeedForwardNetwork() self.net.addInputModule(self.inputLayer) self.net.addModule(self.hiddenLayer) self.net.addOutputModule(self.outputLayer) self.inputToHidden = FullConnection(self.inputLayer,self.hiddenLayer) self.hiddenToOutput = FullConnection(self.hiddenLayer,self.outputLayer) self.net.addConnection(self.inputToHidden) self.net.addConnection(self.hiddenToOutput) self.net.sortModules()
def construct(self, sensor_states, behaviors):
input_len = len(sensor_states[0])
state_len = input_len + len(self._behavior_to_list(''))
# Initialize the network
self.net = FeedForwardNetwork()
input_layer = SigmoidLayer(state_len)
hidden_layer = SigmoidLayer( int(state_len * 1.5) )
output_layer = SigmoidLayer(input_len)
input_to_hidden = FullConnection(input_layer, hidden_layer)
hidden_to_output = FullConnection(hidden_layer, output_layer)
self.net.addInputModule( input_layer )
self.net.addModule( hidden_layer )
self.net.addOutputModule( output_layer )
self.net.addConnection(input_to_hidden)
self.net.addConnection(hidden_to_output)
self.net.sortModules()
# Build the data set
ds = SupervisedDataSet(state_len, input_len)
previous_state = sensor_states[0]
for i in range(1, len(sensor_states) - 1):
behavior = behaviors[i-1]
current_state = sensor_states[i]
a = tuple( previous_state + self._behavior_to_list(behavior) )
b = tuple( current_state )
ds.addSample(a, b)
# Train the network
trainer = BackpropTrainer(self.net, ds, learningrate=0.3)
for i in range(1000):
t1 = datetime.datetime.now()
err = trainer.train()
t2 = datetime.datetime.now()
print '%d: %f (%s)' % (i, err, t2 - t1)
if self.training_callback is not None:
self.training_callback(i, self)
def createJeffersonStyleNetwork(in_count=2,
hidden_count=5,
output_count=4,
recurrent=True,
in_to_out_connect=True,
name=None):
"""
Creates a Jefferson-esque neural network for trail problem.
Returns:
pybrain.network. The neural network.
"""
if recurrent:
ret_net = RecurrentNetwork(name=name)
else:
ret_net = FeedForwardNetwork(name=name)
in_layer = LinearLayer(in_count, name="food")
hidden_layer = SigmoidLayer(hidden_count, name="hidden")
output_layer = LinearLayer(output_count, name="move")
ret_net.addInputModule(in_layer)
ret_net.addModule(hidden_layer)
ret_net.addOutputModule(output_layer)
in_to_hidden = FullConnection(in_layer, hidden_layer)
hidden_to_out = FullConnection(hidden_layer, output_layer)
ret_net.addConnection(in_to_hidden)
ret_net.addConnection(hidden_to_out)
if in_to_out_connect:
in_to_out = FullConnection(in_layer, output_layer)
ret_net.addConnection(in_to_out)
if recurrent:
hidden_to_hidden = FullConnection(hidden_layer, hidden_layer)
ret_net.addRecurrentConnection(hidden_to_hidden)
ret_net.sortModules()
return ret_net
def __init__(self,n_in,n_hidden,n_out):
self.net = FeedForwardNetwork()
inLayer = LinearLayer(n_in)
hiddenLayer1 = SigmoidLayer(n_hidden)
hiddenLayer2 = SigmoidLayer(n_hidden)
outLayer = LinearLayer(n_out)
self.net.addInputModule(inLayer)
self.net.addModule(hiddenLayer1)
self.net.addModule(hiddenLayer2)
self.net.addOutputModule(outLayer)
in_to_hidden = FullConnection(inLayer, hiddenLayer1)
hidden_to_out = FullConnection(hiddenLayer2, outLayer)
hidden_to_hidden = FullConnection(hiddenLayer1, hiddenLayer2)
self.net.addConnection(in_to_hidden)
self.net.addConnection(hidden_to_hidden)
self.net.addConnection(hidden_to_out)
self.net.sortModules()
#self.net.params
self.ds = SupervisedDataSet(n_in, n_out)
def __init__(self, datadir, insize=None, outsize=None, paramfile=None):
self.datadir = datadir
if insize == None:
g = runner.Game()
ip = self._game2input(g)
self.insize = len(ip)
else:
self.insize = insize
if outsize == None:
self.outsize = 1
else:
self.outsize = outsize
if paramfile:
f = os.path.join(self.datadir, paramfile)
self.nn = NetworkReader.readFrom(f)
try:
self.name = re.search("(.*)-bestof-(.*)", paramfile).group(1)
except AttributeError:
self.name = "blondie-%s" % (datetime.datetime.now())
else:
self.nn = FeedForwardNetwork()
tmpname = "blondie-%s" % (datetime.datetime.now())
self.name = re.sub("[.: ]", "-", tmpname)
inLayer = LinearLayer(self.insize)
hiddenLayer1 = SigmoidLayer(self.insize)
hiddenLayer2 = SigmoidLayer(self.insize)
outLayer = LinearLayer(self.outsize)
self.nn.addInputModule(inLayer)
self.nn.addModule(hiddenLayer1)
self.nn.addModule(hiddenLayer2)
self.nn.addOutputModule(outLayer)
in_to_hidden1 = FullConnection(inLayer, hiddenLayer1)
hidden1_to_hidden2 = FullConnection(hiddenLayer1, hiddenLayer2)
hidden2_to_out = FullConnection(hiddenLayer2, outLayer)
self.nn.addConnection(in_to_hidden1)
self.nn.addConnection(hidden1_to_hidden2)
self.nn.addConnection(hidden2_to_out)
self.nn.sortModules()
def initNetwork(self):
#Intiailize Neural Nets
self.neuralNet = FeedForwardNetwork()
#Define and add each set of layers
inLayer = LinearLayer(5)
hiddenLayer = SigmoidLayer(15)
outLayer = LinearLayer(5)
self.neuralNet.addInputModule(inLayer)
self.neuralNet.addModule(hiddenLayer)
self.neuralNet.addOutputModule(outLayer)
#Create conenctions
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_out = FullConnection(hiddenLayer, outLayer)
self.neuralNet.addConnection(in_to_hidden)
self.neuralNet.addConnection(hidden_to_out)
#Sort the NeuralNet
self.neuralNet.sortModules()
#Add supervised data sets
ds = SupervisedDataSet(NNInitializer.NUMBER_OF_INPUTS, NNInitializer.NUMBER_OF_OUTPUTS)
inputSet, outputSet = self.loadTrainingSet('scents_based_input',
'scents_based_output')
#inputSet, outputSet = self.generateTrainingSet()
print "Adding samples to data set...."
for i,val in enumerate(inputSet):
# print "Input Set: "
# print inputSet[i]
# print "Output Set: "
# print outputSet[i]
ds.addSample(inputSet[i], outputSet[i])
print "Done."
print "Starting training...."
#Perform Training
trainer = BackpropTrainer(self.neuralNet, ds)
trainer.train()
print "Done."
def init_network(self, inputs, targets):
""" Build the network as a full-connected feed-forward net.
Uses the softmax function for the output layer as recommended for classification"""
self.n = FeedForwardNetwork()
inLayer = LinearLayer(inputs, name='in' )
hiddenLayer = SigmoidLayer(self.hidden_layer, name='hidden')
outLayer = SoftmaxLayer(targets, name='out')
self.n.addInputModule(inLayer)
self.n.addModule(hiddenLayer)
self.n.addOutputModule(outLayer)
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_out = FullConnection(hiddenLayer, outLayer)
self.n.addConnection(in_to_hidden)
self.n.addConnection(hidden_to_out)
self.n.sortModules()
def __init__(self):
super(NeuralNetworkPlayer, self).__init__()
# Create the network
self.net = FeedForwardNetwork()
# Internal Layers
inLayer = LinearLayer(5)
hiddenLayer1 = SigmoidLayer(6)
hiddenLayer2 = SigmoidLayer(6)
outLayer = LinearLayer(7)
self.net.addInputModule(inLayer)
self.net.addModule(hiddenLayer1)
self.net.addModule(hiddenLayer2)
self.net.addOutputModule(outLayer)
self.net.addConnection(FullConnection(inLayer, hiddenLayer1))
self.net.addConnection(FullConnection(hiddenLayer1, hiddenLayer2))
self.net.addConnection(FullConnection(hiddenLayer2, outLayer))
self.net.sortModules()
def __init__(self, hidden_layers, ally_champ_obj_list, enemy_champ_obj_list):
self.ally_champ_obj_list = ally_champ_obj_list
self.enemy_champ_obj_list = enemy_champ_obj_list
self.set_nodes()
self.network = FeedForwardNetwork()
connect_queue = Queue.Queue()
for layer in xrange(0, hidden_layers):
connect_queue.put(TanhLayer(self.input_node_count, name = 'hidden_layer_{}'.format(layer)))
connect_queue.put(SigmoidLayer(1, name = 'output_layer'))
prev_layer = LinearLayer(self.input_node_count, name = 'input_layer')
self.network.addInputModule(prev_layer)
while not connect_queue.empty():
current_layer = connect_queue.get()
if current_layer.name == 'output_layer':
self.network.addOutputModule(current_layer)
else:
self.network.addModule(current_layer)
bias = BiasUnit()
bias_connection = FullConnection(bias, current_layer, name = "bias_to_{}_connection".format(current_layer.name))
self.network.addModule(bias)
self.network.addConnection(bias_connection)
connection = FullConnection(prev_layer, current_layer, name = "{}_to_{}_connection".format(prev_layer.name, current_layer.name))
self.network.addConnection(connection)
prev_layer = current_layer
self.network.sortModules()
def PrepareModel(self, savedmodel = None): if savedmodel != None: self.trainer = savedmodel else: attributescount=len(self.traindata[0]) nrclass = len(set(self.trainlabel)) self.ds = ClassificationDataSet(attributescount, target=nrclass, nb_classes=nrclass, class_labels=list(set(self.trainlabel))) for i in range(len(self.traindata)): self.ds.appendLinked(self.traindata[i], [self.trainlabel[i]]) self.ds._convertToOneOfMany() self.net = FeedForwardNetwork() inLayer = LinearLayer(len(self.traindata[0])) self.net.addInputModule(inLayer) hiddenLayers=[] for i in range(self.hiddenlayerscount): hiddenLayer=SigmoidLayer(self.hiddenlayernodescount) hiddenLayers.append(hiddenLayer) self.net.addModule(hiddenLayer) outLayer = SoftmaxLayer(nrclass) self.net.addOutputModule(outLayer) layers_connections=[] layers_connections.append(FullConnection(inLayer, hiddenLayers[0])) for i in range(self.hiddenlayerscount-1): layers_connections.append(FullConnection(hiddenLayers[i-1], hiddenLayers[i])) layers_connections.append(FullConnection(hiddenLayers[-1], outLayer)) for layers_connection in layers_connections: self.net.addConnection(layers_connection) self.net.sortModules() #training the network self.trainer = BackpropTrainer(self.net, self.ds) self.trainer.train()
class NeuralNet:
def __init__(self, hidden_neuron_num=1, hidden_type='sigmoid'):
self.hidden_neuron_num = hidden_neuron_num
self.hidden_type = hidden_type
self.net = FeedForwardNetwork()
self.samples = SupervisedDataSet(784, 784)
self.vectorizer = ImageVectorizer()
self.add_layers()
self.add_connections()
self.sort()
def add_layers(self):
self.inLayer = LinearLayer(784, name='in')
self.outLayer = LinearLayer(784, name='out')
if self.hidden_type == 'sigmoid':
self.hiddenLayer = SigmoidLayer(self.hidden_neuron_num, name='hidden')
else:
# I found I had to overwrite the output layer to sigmoid to get the
# hidden layer to work as linear
self.hiddenLayer = LinearLayer(self.hidden_neuron_num, name='hidden')
self.outLayer = SigmoidLayer(784, name='out')
self.net.addInputModule(self.inLayer)
self.net.addModule(self.hiddenLayer)
self.net.addOutputModule(self.outLayer)
def add_connections(self):
self.in_to_hidden = FullConnection(self.inLayer, self.hiddenLayer)
self.hidden_to_out = FullConnection(self.hiddenLayer, self.outLayer)
self.net.addConnection(self.in_to_hidden)
self.net.addConnection(self.hidden_to_out)
def sort(self):
self.net.sortModules()
def activate(self, vector):
return self.net.activate(vector)
def train(self, paths):
for path in paths:
vector = self.vectorizer.image_to_vector(path)
vector = numpy.float64([el / 255.0 for el in vector])
self.samples.addSample(vector, vector)
trainer = BackpropTrainer(self.net, self.samples, learningrate=.5, lrdecay=0.98)
for i in range(1,20):
error = trainer.train()
print "error for %(i)ith iteration: %(error)f" % locals()
def input_weights_of_hidden_layer(self):
weights = self.in_to_hidden.params
hidden_weights_by_neuron = numpy.split(weights, self.hidden_neuron_num)
return hidden_weights_by_neuron
def input_weights_of_out_layer(self):
weights = self.hidden_to_out.params
hidden_weights_by_neuron = numpy.split(weights, self.hidden_neuron_num)
return hidden_weights_by_neuron
from pybrain.structure import FeedForwardNetwork
from pybrain.structure import LinearLayer, SigmoidLayer, SoftmaxLayer
from pybrain.supervised.trainers import BackpropTrainer
from pybrain.structure import FullConnection
from pybrain.datasets import SupervisedDataSet
import numpy
size_x = 20
hidden = 10
net = FeedForwardNetwork()
inLayer = LinearLayer(size_x * size_x)
hiddenLayer = SigmoidLayer(hidden)
outLayer = LinearLayer(size_x * size_x)
net.addInputModule(inLayer)
net.addModule(hiddenLayer)
net.addOutputModule(outLayer)
in_to_hidden = FullConnection(inLayer, hiddenLayer)
hidden_to_out = FullConnection(hiddenLayer, outLayer)
net.addConnection(in_to_hidden)
net.addConnection(hidden_to_out)
net.sortModules()
print "Adding Samples"
ds = SupervisedDataSet(size_x * size_x, size_x * size_x)
for i in range(1000):
data = numpy.random.randn(size_x * size_x)
ds.addSample(data, data)
print "Training"
trainer = BackpropTrainer(net, ds)
for i in range(100):
noise30Data = np.load('dataset30noise.npy')[0:2000]
labels = np.load('datalabels.npy')[0:2000]
testSet = np.load('testdata.npy')[0:5000]
test5noise = np.load('test5noise.npy')[0:5000]
test10noise = np.load('test10noise.npy')[0:5000]
test15noise = np.load('test15noise.npy')[0:5000]
test20noise = np.load('test20noise.npy')[0:5000]
test25noise = np.load('test25noise.npy')[0:5000]
test30noise = np.load('test30noise.npy')[0:5000]
testLabels = np.load('testlabels.npy')[0:5000]
print "data loaded"
inputComponents = np.shape(dataSet)[1]
outputComponents = 10
network = FeedForwardNetwork()
inputLayer = LinearLayer(inputComponents,name='input')
hiddenLayer = SigmoidLayer(inputComponents, name='hidden')
outputLayer = SigmoidLayer(outputComponents,name='out')
data = ClassificationDataSet(inputComponents, 1, nb_classes = 10)
in_hidden = FullConnection(inputLayer, hiddenLayer)
hidden_out = FullConnection(hiddenLayer, outputLayer)
network.addInputModule(inputLayer)
network.addModule(hiddenLayer)
network.addOutputModule(outputLayer)
network.addConnection(in_hidden)
network.addConnection(hidden_out)
import math import numpy as np import scipy as sp from scipy import ndimage, misc import random import skimage from skimage import data, filter, io import matplotlib.pyplot as plt from pybrain.tools.shortcuts import buildNetwork from pybrain.datasets import SupervisedDataSet from pybrain.supervised.trainers import BackpropTrainer from pybrain.structure import FeedForwardNetwork, LinearLayer, SigmoidLayer, FullConnection net = FeedForwardNetwork() inLayer = LinearLayer(4) hiddenLayer = SigmoidLayer(2) outLayer = LinearLayer(4) net.addInputModule(inLayer) net.addModule(hiddenLayer) net.addOutputModule(outLayer) in_to_hidden = FullConnection(inLayer, hiddenLayer) hidden_to_out = FullConnection(hiddenLayer, outLayer) net.addConnection(in_to_hidden) net.addConnection(hidden_to_out) net.sortModules()
#!/usr/bin/env python from pybrain.structure import FeedForwardNetwork from pybrain.structure import LinearLayer, SigmoidLayer from pybrain.structure import FullConnection #Se construye la red n = FeedForwardNetwork() #Se construyen las capas inLayer = LinearLayer(2, name="input") hiddenLayer = SigmoidLayer(3, name="hid") outLayer = LinearLayer(1, name="output") #Se agregan las capas a la red n.addInputModule(inLayer) n.addModule(hiddenLayer) n.addOutputModule(outLayer) #Se conectan las capas in_to_hidden = FullConnection(inLayer, hiddenLayer, name="con1") hidden_to_out = FullConnection(hiddenLayer, outLayer, name="con2") #Se agregan las conexiones n.addConnection(in_to_hidden) n.addConnection(hidden_to_out) #All the elements are in place now, so we can do the final step that makes our MLP usable, which is to call the .sortModules() method: n.sortModules() print n print n.activate([3,7])