def trainedLSTMNN2():
"""
n = RecurrentNetwork()
inp = LinearLayer(100, name = 'input')
hid = LSTMLayer(30, name='hidden')
out = LinearLayer(1, name='output')
#add modules
n.addOutputModule(out)
n.addInputModule(inp)
n.addModule(hid)
#add connections
n.addConnection(FullConnection(inp, hid))
n.addConnection(FullConnection(hid, out))
n.addRecurrentConnection(FullConnection(hid, hid))
n.sortModules()
"""
n = buildSimpleLSTMNetwork()
print "Network created"
d = load1OrderDataSet()
print "Data loaded"
t = RPropMinusTrainer(n, dataset=d, verbose=True)
t.trainUntilConvergence()
exportANN(n)
return n
def trainedLSTMNN2():
"""
n = RecurrentNetwork()
inp = LinearLayer(100, name = 'input')
hid = LSTMLayer(30, name='hidden')
out = LinearLayer(1, name='output')
#add modules
n.addOutputModule(out)
n.addInputModule(inp)
n.addModule(hid)
#add connections
n.addConnection(FullConnection(inp, hid))
n.addConnection(FullConnection(hid, out))
n.addRecurrentConnection(FullConnection(hid, hid))
n.sortModules()
"""
n = buildSimpleLSTMNetwork()
print "Network created"
d = load1OrderDataSet()
print "Data loaded"
t = RPropMinusTrainer(n, dataset=d, verbose=True)
t.trainUntilConvergence()
exportANN(n)
return n
train_errors = [] # save errors for plotting later
EPOCHS_PER_CYCLE = 5
CYCLES = 100
EPOCHS = EPOCHS_PER_CYCLE * CYCLES
for i in xrange(CYCLES):
trainer.trainEpochs(EPOCHS_PER_CYCLE)
train_errors.append(trainer.testOnData())
epoch = (i + 1) * EPOCHS_PER_CYCLE
print("\r epoch {}/{}".format(epoch, EPOCHS))
stdout.flush()
print()
print("final error =", train_errors[-1])
for sample, target in zip(X_test, y_test):
print(" sample = ", sample)
print("predicted next sample = ", net.activate(sample))
print(" actual next sample = ", target)
print()
plt.plot(range(0, EPOCHS, EPOCHS_PER_CYCLE), train_errors)
plt.xlabel('epoch')
plt.ylabel('error')
plt.show()
exit()
print net.activate([2, 1, 1, 2])
trainer = BackpropTrainer(net, ds)
print trainer.trainUntilConvergence()
from pybrain.supervised.trainers import BackpropTrainer
