def exportCatDogRNN(net, fileName=root.path() + "/res/cat_dog_nm_params"):
# arr = net.params
# np.save(fileName, arr)
# fileObject = open(fileName+'.pickle', 'w')
# pickle.dump(net, fileObject)
# fileObject.close()
NetworkWriter.writeToFile(net, fileName + '.xml')
def exportCatDogRFCNN(net, fileName = root.path()+"/res/cat_dog_fc_params"):
# arr = net.params
# np.save(fileName, arr)
# fileObject = open(fileName+'.pickle', 'w')
# pickle.dump(net, fileObject)
# fileObject.close()
NetworkWriter.writeToFile(net, fileName+'.xml')
def xmlInvariance(n, forwardpasses = 1):
""" try writing a network to an xml file, reading it, rewrite it, reread it, and compare
if the result looks the same (compare string representation, and forward processing
of some random inputs) """
tmpfile = tempfile.NamedTemporaryFile()
f = tmpfile.name
NetworkWriter.writeToFile(n, f)
tmpnet = NetworkReader.readFrom(f)
NetworkWriter.writeToFile(tmpnet, f)
endnet = NetworkReader.readFrom(f)
netCompare(tmpnet, endnet, forwardpasses, True)
def xmlInvariance(n, forwardpasses=1):
""" try writing a network to an xml file, reading it, rewrite it, reread it, and compare
if the result looks the same (compare string representation, and forward processing
of some random inputs) """
tmpfile = tempfile.NamedTemporaryFile()
f = tmpfile.name
NetworkWriter.writeToFile(n, f)
tmpnet = NetworkReader.readFrom(f)
NetworkWriter.writeToFile(tmpnet, f)
endnet = NetworkReader.readFrom(f)
netCompare(tmpnet, endnet, forwardpasses, True)
def build_net(self):
if os.path.exists(self.NET_FILE):
return NetworkReader.readFrom(self.NET_FILE)
ds = ClassificationDataSet(len(feats), nb_classes=len(classes))
for c in classes:
print c
with codecs.open(os.path.join(self.data_root, c+".txt"), 'r', 'utf8') as f:
for line in f:
r = Record("11", line, c, "")
ds.appendLinked(r.features(), [r.class_idx()])
ds._convertToOneOfMany([0, 1])
net = buildNetwork(ds.indim, int((ds.indim + ds.outdim)/2), ds.outdim, bias=True, hiddenclass=TanhLayer, outclass=SoftmaxLayer)
trainer = BackpropTrainer(net, ds, momentum=0.75, verbose=True)
trainer.trainUntilConvergence(maxEpochs=300)
NetworkWriter.writeToFile(net, self.NET_FILE)
return net
def train():
f = open('train.csv', 'r')
csv_reader = csv.reader(f)
dataset = SupervisedDataSet(64, 1)
for d in csv_reader:
dataset.addSample(d[0:64], d[64])
network = buildNetwork(64, 19, 1)
trainer = BackpropTrainer(network, dataset)
for i in range(100):
trainer.train()
NetworkWriter.writeToFile(network, "model.xml")
f.close()
def xmlInvariance(n, forwardpasses = 1):
""" try writing a network to an xml file, reading it, rewrite it, reread it, and compare
if the result looks the same (compare string representation, and forward processing
of some random inputs) """
# We only use this for file creation.
tmpfile = tempfile.NamedTemporaryFile(dir=".")
f = tmpfile.name
tmpfile.close()
NetworkWriter.writeToFile(n, f)
tmpnet = NetworkReader.readFrom(f)
NetworkWriter.writeToFile(tmpnet, f)
endnet = NetworkReader.readFrom(f)
# Unlink temporary file.
os.unlink(f)
netCompare(tmpnet, endnet, forwardpasses, True)
def train():
f = open('train_tower.csv', 'r')
csvreader = csv.reader(f)
dataset = SupervisedDataSet(64, 2)
for d in csvreader:
if d[64] == '0':
dataset.addSample(d[0:64], [1, 0])
else:
dataset.addSample(d[0:64], [0, 1])
network = buildNetwork(64, 19, 2)
trainer = BackpropTrainer(network, dataset)
for i in range(100):
trainer.train()
trainer.testOnData(dataset, verbose=True)
NetworkWriter.writeToFile(network, "tower.xml")
f.close()
def xmlInvariance(n, forwardpasses = 1):
""" try writing a network to an xml file, reading it, rewrite it, reread it, and compare
if the result looks the same (compare string representation, and forward processing
of some random inputs) """
import os.path
f = 'temp/xmlInvarianceTest.xml'
if os.path.split(os.path.abspath(os.path.curdir))[1] == 'unittests':
f = '../'+f
NetworkWriter.writeToFile(n, f)
tmpnet = NetworkReader.readFrom(f)
NetworkWriter.writeToFile(tmpnet, f)
endnet = NetworkReader.readFrom(f)
if str(n) == str(endnet):
print 'Same representation'
else:
print n
print "-" * 80
print endnet
outN = zeros(n.outdim)
outEnd = zeros(endnet.outdim)
n.reset()
endnet.reset()
for dummy in range(forwardpasses):
inp = randn(n.indim)
outN += n.activate(inp)
outEnd += endnet.activate(inp)
if sum(map(abs, outN - outEnd)) < 1e-9:
print 'Same function'
else:
print outN
print outEnd
if n.__class__ == endnet.__class__:
print 'Same class'
else:
print n.__class__
print endnet.__class__
def xmlInvariance(n, forwardpasses=1):
""" try writing a network to an xml file, reading it, rewrite it, reread it, and compare
if the result looks the same (compare string representation, and forward processing
of some random inputs) """
import os.path
f = 'temp/xmlInvarianceTest.xml'
if os.path.split(os.path.abspath(os.path.curdir))[1] == 'unittests':
f = '../' + f
NetworkWriter.writeToFile(n, f)
tmpnet = NetworkReader.readFrom(f)
NetworkWriter.writeToFile(tmpnet, f)
endnet = NetworkReader.readFrom(f)
if str(n) == str(endnet):
print 'Same representation'
else:
print n
print "-" * 80
print endnet
outN = zeros(n.outdim)
outEnd = zeros(endnet.outdim)
n.reset()
endnet.reset()
for dummy in range(forwardpasses):
inp = randn(n.indim)
outN += n.activate(inp)
outEnd += endnet.activate(inp)
if sum(map(abs, outN - outEnd)) < 1e-9:
print 'Same function'
else:
print outN
print outEnd
if n.__class__ == endnet.__class__:
print 'Same class'
else:
print n.__class__
print endnet.__class__
def saveNetwork(self, fname):
""" save the trained network to a file """
NetworkWriter.writeToFile(self.Trainer.module, fname)
logging.info("Network saved to: "+fname)
def saveNetwork(self, fname):
""" save the trained network to a file """
NetworkWriter.writeToFile(self.Trainer.module, fname)
logging.info("Network saved to: "+fname)
def save(self, file_path):
NetworkWriter.writeToFile(self.network, file_path)
def export_network(network, file_path):
NetworkWriter.writeToFile(network, file_path)
outputTest = net.activateOnDataset(test_data)
outputTest = outputTest.argmax(axis=1)
testResult = percentError(outputTest, real_test)
finalTrainResult = 100 - trainResult
finalTestResult = 100 - testResult
print "Epoch: " + str(i + 1) + "\tTraining set accuracy: " + str(finalTrainResult) + "\tTest set accuracy: " + str(
finalTestResult)
# getStatistics( )
trainResultArr.append(finalTestResult)
testResultArr.append(finalTrainResult)
epochs.append(i)
prediction = net.activate(test_input)
# returns the index of the highest value down the columns
p = argmax(prediction, axis=0)
NetworkWriter.writeToFile(net, 'extra_layers.xml')
plt.plot(epochs, trainResultArr)
plt.plot(epochs, testResultArr)
plt.title('Training Result (Orange) vs Test Result of ANN (Blue)')
plt.xlabel('Epochs')
plt.ylabel('Accuracy %')
plt.show()
trainResultArr.append((finalTestRes))
testResultArr.append((finalTrainRes))
trainResultArrHB.append((finalTestResHB))
testResultArrHB.append((finalTrainResHB))
epochs.append((i))
X1 = im3.reshape((X.shape[1]))
prediction = net.activate(X1)
predictionHB = netHB.activate(X1)
# returns the index of the highest value down the columns
p = argmax(prediction, axis=0)
pHB = argmax(predictionHB, axis=0)
NetworkWriter.writeToFile(net, 'dig.xml')
print("predicted output after training is", p)
NetworkWriter.writeToFile(netHB, 'digHB.xml')
print(
"predicted output after training net with hyperbolic activation function is",
pHB)
plt.plot(epochs, trainResultArr)
plt.plot(epochs, testResultArr)
plt.plot(epochs, trainResultArrHB)
plt.plot(epochs, testResultArrHB)
plt.title('Training Result (Orange) vs Test Result of ANN (Blue)')
plt.xlabel('Epochs')
plt.ylabel('Accuracy %')
outputTest = net.activateOnDataset(test_data)
outputTest = outputTest.argmax(axis=1)
testResult = percentError(outputTest, real_test)
finalTrainRes = 100 - trainResult
finalTestRes = 100 - testResult
print "Epoch: " + str(i) + "\tTraining set accuracy: " + str(finalTrainRes) + "\tTest set accuracy: " + str(finalTestRes)
trainResultArr.append((finalTestRes))
testResultArr.append((finalTrainRes))
epochs.append((i))
X1 = im3.reshape((X.shape[1]))
prediction = net.activate(X1)
# returns the index of the highest value down the columns
p = argmax(prediction, axis=0)
NetworkWriter.writeToFile(net, 'dig_img_from_dir.xml')
print("predicted output after training is", p)
plt.plot(epochs,trainResultArr)
plt.plot(epochs,testResultArr)
plt.title('Training Result (Orange) vs Test Result of ANN (Blue)')
plt.xlabel('Epochs')
plt.ylabel('Accuracy %')
plt.show()
def write_to_file(self, fnn):
path_to_file = self.get_path()
NetworkWriter.writeToFile(fnn, path_to_file)
# Predefine iterations: epochs & cycles
EPOCHS_PER_CYCLE = 5
CYCLES = 100
EPOCHS = EPOCHS_PER_CYCLE * CYCLES
# Training loop
for i in xrange(CYCLES):
trainer.trainEpochs(EPOCHS_PER_CYCLE)
error = trainer.testOnData()
epoch = (i + 1) * EPOCHS_PER_CYCLE
print("\r Epoch: {}/{} Error: {}".format(epoch, EPOCHS, error), end="")
stdout.flush()
# Save model
NetworkWriter.writeToFile(rnn, 'rnn3.xml')
# Ad hoc test
for test in test_data:
for i in xrange(0, len(test) - 6, 5):
# Get 5 obs, 6th we wish to predict
obs, nxt = test[i:i + 5], test[i + 6]
# Predict all
prds = map(rnn.activate, obs)
# Get 6th prediction
prd = prds.pop()[0]
# Test if prd is anomalous
anm = prd > (1 + np.mean(obs) + 2 * np.std(obs))
# Get previous 5 obs,prd error rate
def save_net():
from pybrain.tools.xml import NetworkWriter
save_filename = tkFileDialog.asksaveasfilename()
NetworkWriter.writeToFile(net,save_filename)
for single_npz in training_data:
with np.load(single_npz) as data:
print data.files
train_temp = data['train']
train_labels_temp = data['train_labels']
print (train_temp.shape)
print (train_labels_temp.shape)
image_array = np.vstack((image_array, train_temp))
label_array = np.vstack((label_array, train_labels_temp))
t1 = time.time()
for i in range(train_temp.shape[0]):
target.addSample(image_array[i],label_array[i])
print 'loading time : ' , time.time() - t1
# train
while True:
try:
while True:
errors = trainer.train()
if (j % 5) == 0:
print ("epoch%d error : %f" % (j, errors))
elif(errors < 2e-2) :
print ("epoch%d error : %f" % (j, errors))
break
j += 1
finally:
NetworkWriter.writeToFile(network, XML)
break
raw_input('>')
def savenet(net):
fileObject = open('C:\\Users\\hardy_000\\Documents\\datasci\\net', 'w')
pickle.dump(net, fileObject)
NetworkWriter.writeToFile(net, 'C:\\Users\\hardy_000\\Documents\\datasci\\net.xml')
fileObject.close()
