outputVector = [0, 0, 0, 0]
if index == 'A':
outputVector[0] = 1
if index == 'B':
outputVector[1] = 1
if index == 'C':
outputVector[2] = 1
if index == 'D':
outputVector[3] = 1
for item in inputSequence:
trainingData.appendLinked(codeTable[item].values, outputVector)
# Construct trainer and train network
#trainer = RPropMinusTrainer(rnn, verbose=True)
trainer = BackpropTrainer(rnn, learningrate=0.01, lrdecay=0.99, momentum=0, verbose=True, batchlearning=False, weightdecay=0)
trainer.trainUntilConvergence(trainingData, validationData=None, validationProportion=0.25, maxEpochs=10)
# Clean up memory
trainer = []
trainingData = []
df = []
# Compute predictions on test data
outputVector = [0, 0, 0, 0]
if index == 'A':
outputVector[0] = 1
if index == 'B':
outputVector[1] = 1
if index == 'C':
outputVector[2] = 1
if index == 'D':
outputVector[3] = 1
for item in inputSequence:
trainingData.appendLinked(codeTable[item].values, outputVector)
# Construct trainer and train network
#trainer = RPropMinusTrainer(rnn, verbose=True)
trainer = BackpropTrainer(rnn,
learningrate=0.01,
lrdecay=0.99,
momentum=0,
verbose=True,
batchlearning=False,
weightdecay=0)
trainer.trainUntilConvergence(trainingData,
validationData=None,
validationProportion=0.25,
maxEpochs=10)
r = [int(x) for x in bin(an+bn)[2:]]
while len(a) < len(r):
a = [0] + a
while len(b) < len(r):
b = [0] + b
a = a[::-1]
b = b[::-1]
r = r[::-1]
ds.newSequence()
for i in range(len(a)):
inl = [a[i], b[i]]
out = [r[i]]
ds.appendLinked(inl, out)
#trainer = RPropMinusTrainer(n, dataset = ds)
trainer = BackpropTrainer(n, dataset = ds)
print("Generating dataset took", time()-start)
lastlen = 0
start = time()
try:
while True:
epochstart = time()
error = trainer.train()
tpe = time()-epochstart
