def __init__(self, module, dataset = None, init_std = 0.01,
noise_std = 0.1, learning_rate = 0.3):
for m in module.modules:
if m in module.inmodules or m in module.outmodules:
continue
if isinstance(m, NeuronLayer) and not isinstance(m, BiasUnit) \
and not isinstance(m, TanhLayer):
raise ValueError("Only tanh hidden layers are supported.")
self.setData(dataset)
self.init_std = init_std
self.noise_std = noise_std
self.lrate = learning_rate
self._crbms = []
self._modules = []
Trainer.__init__(self, module)
def __init__(self, module, dataset=None, learningrate=0.01, lrdecay=1.0,
momentum=0., verbose=False, batchlearning=False,
weightdecay=0.):
Trainer.__init__(self, module)
self.setData(dataset)
self.verbose = verbose
self.batchlearning = batchlearning
self.weightdecay = weightdecay
self.epoch = 0
self.totalepochs = 0
# set up gradient descender
self.descent = GradientDescent()
self.descent.alpha = learningrate
self.descent.momentum = momentum
self.descent.alphadecay = lrdecay
self.descent.init(module.params)
def __init__(self, module, dataset=None):
Trainer.__init__(self, module)
#self.setData(dataset)
self.ds = dataset
self.learner = PGMLearner()