def testBatchTraining(hidden=15, n=None):
d = XORDataSet()
if n is None:
n = buildNetwork(d.indim, hidden, d.outdim, recurrent=False)
provider = ModuleWrapper(d, n, shuffling=False)
algo = SGD(provider, n.params.copy(), callback=printy, learning_rate=0.04, batch_size=4)
algo.run(250)
def testNewTraining3(hidden=15, n=None):
d = XORDataSet(True)
if n is None:
n = buildNetwork(d.indim, hidden, d.outdim, recurrent=False)
provider = ClassificationModuleWrapper(d, n, shuffling=False)
algo = SGD(provider, n.params.copy(), callback=printy, learning_rate=0.01, momentum=0.99)
algo.run(1000)
def testBatchTraining(hidden=15, n=None):
d = XORDataSet()
if n is None:
n = buildNetwork(d.indim, hidden, d.outdim, recurrent=False)
provider = ModuleWrapper(d, n, shuffling=False)
algo = SGD(provider,
n.params.copy(),
callback=printy,
learning_rate=0.04,
batch_size=4)
algo.run(250)
def testNewTraining3(hidden=15, n=None):
d = XORDataSet(True)
if n is None:
n = buildNetwork(d.indim, hidden, d.outdim, recurrent=False)
provider = ClassificationModuleWrapper(d, n, shuffling=False)
algo = SGD(provider,
n.params.copy(),
callback=printy,
learning_rate=0.01,
momentum=0.99)
algo.run(1000)
def testCE(hidden=15):
""" Test when doing the classification using the cross-entropy loss."""
d = XORDataSet(True)
n = buildNetwork(d.indim, hidden, d.outdim, recurrent=False)
p0 = n.params.copy()
provider = ClassificationModuleWrapper(d, n, shuffling=False)
algo = SGD(provider, n.params.copy(), callback=printy, learning_rate=0.01, momentum=0.99)
print '\n' * 2
print 'SGD-CE'
algo.run(1000)
n._setParameters(p0)
provider = ClassificationModuleWrapper(d, n, shuffling=False)
algo = vSGDfd(provider, n.params.copy(), callback=printy)
print '\n' * 2
print 'vSGD-CE'
algo.run(1000)
def testMinibatch(dim=4):
f = StochQuad(noiseLevel=0.2)
fw = FunctionWrapper(dim, f, record_samples=True)
x0 = ones(dim)
for mb in [1,3,15,250]:
print 'minibatch', mb
algo = SGD(fw, x0, callback=printy, batch_size=mb, learning_rate=0.1)
algo.run(10)
print
[fw.nextSamples(1) for _ in range(2500)]
dw = DataFunctionWrapper(fw._seen, f, shuffling=False)
print 'Fixed samples'
for mb in [1,3,15,250]:
print 'minibatch', mb
dw.reset()
algo = SGD(dw, x0, callback=printy, batch_size=mb, learning_rate=0.1)
algo.run(10)
print
def testMinibatch(dim=4):
f = StochQuad(noiseLevel=0.2)
fw = FunctionWrapper(dim, f, record_samples=True)
x0 = ones(dim)
for mb in [1, 3, 15, 250]:
print "minibatch", mb
algo = SGD(fw, x0, callback=printy, batch_size=mb, learning_rate=0.1)
algo.run(10)
print
[fw.nextSamples(1) for _ in range(2500)]
dw = DataFunctionWrapper(fw._seen, f, shuffling=False)
print "Fixed samples"
for mb in [1, 3, 15, 250]:
print "minibatch", mb
dw.reset()
algo = SGD(dw, x0, callback=printy, batch_size=mb, learning_rate=0.1)
algo.run(10)
print
def testCE(hidden=15):
""" Test when doing the classification using the cross-entropy loss."""
d = XORDataSet(True)
n = buildNetwork(d.indim, hidden, d.outdim, recurrent=False)
p0 = n.params.copy()
provider = ClassificationModuleWrapper(d, n, shuffling=False)
algo = SGD(provider,
n.params.copy(),
callback=printy,
learning_rate=0.01,
momentum=0.99)
print '\n' * 2
print 'SGD-CE'
algo.run(1000)
n._setParameters(p0)
provider = ClassificationModuleWrapper(d, n, shuffling=False)
algo = vSGDfd(provider, n.params.copy(), callback=printy)
print '\n' * 2
print 'vSGD-CE'
algo.run(1000)
def testSGD(dim=3):
f = FunctionWrapper(dim, StochQuad(noiseLevel=0.2))
x0 = ones(dim)
algo = SGD(f, x0, callback=printy, learning_rate=0.2, loss_target=0.01)
algo.run(100)
print
def testBank():
D = readData()
print len(D), 'samples', D.indim, 'features'
from pybrain import LinearLayer, FullConnection, FeedForwardNetwork, BiasUnit, SigmoidLayer
net = FeedForwardNetwork()
net.addInputModule(LinearLayer(D.indim, name='in'))
net.addModule(BiasUnit(name='bias'))
net.addOutputModule(SigmoidLayer(1, name='out'))
net.addConnection(FullConnection(net['in'], net['out']))
net.addConnection(FullConnection(net['bias'], net['out']))
net.sortModules()
p = net.params
p *= 0.01
provider = ModuleWrapper(D, net, shuffling=False)
algo = SGD(provider, net.params.copy(), #callback=printy,
learning_rate=5.5e-5)
#algo = vSGDfd(provider, net.params.copy(), #callback=printy
# )
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
def testSGD(dim=3):
f = FunctionWrapper(dim, StochQuad(noiseLevel=0.2))
x0 = ones(dim)
algo = SGD(f, x0, callback=printy, learning_rate=0.2, loss_target=0.01)
algo.run(100)
print
def testBank():
D = readData()
print len(D), 'samples', D.indim, 'features'
from pybrain import LinearLayer, FullConnection, FeedForwardNetwork, BiasUnit, SigmoidLayer
net = FeedForwardNetwork()
net.addInputModule(LinearLayer(D.indim, name='in'))
net.addModule(BiasUnit(name='bias'))
net.addOutputModule(SigmoidLayer(1, name='out'))
net.addConnection(FullConnection(net['in'], net['out']))
net.addConnection(FullConnection(net['bias'], net['out']))
net.sortModules()
p = net.params
p *= 0.01
provider = ModuleWrapper(D, net, shuffling=False)
algo = SGD(
provider,
net.params.copy(), #callback=printy,
learning_rate=5.5e-5)
#algo = vSGDfd(provider, net.params.copy(), #callback=printy
# )
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
algo.run(len(D))
printy(algo, force=True)
