def __init__(self, input=None, label=None, n_ins=2, hidden_layer_sizes=[3, 3], n_outs=2, numpy_rng=None):
self.x = input
self.y = label
self.sigmoid_layers = []
self.rbm_layers = []
self.n_layers = len(hidden_layer_sizes)
if numpy_rng is None:
numpy_rng = numpy.random.RandomState(1234)
assert self.n_layers > 0
# construct multi-layer
for i in xrange(self.n_layers):
# layer input size
if i == 0:
input_size = n_ins
else:
input_size = hidden_layer_sizes[i - 1]
# layer input
if i == 0:
layer_input = self.x
else:
layer_input = self.sigmoid_layers[-1].sample_h_given_v()
# construct sigmoid_layers
sigmoid_layer = HiddenLayer(
input=layer_input, n_in=input_size, n_out=hidden_layer_sizes[i], numpy_rng=numpy_rng, activation=sigmoid
)
self.sigmoid_layers.append(sigmoid_layer)
# construct rbm_layers
rbm_layer = RBM(
input=layer_input,
n_visible=input_size,
n_hidden=hidden_layer_sizes[i],
W=sigmoid_layer.W,
hbias=sigmoid_layer.b,
)
self.rbm_layers.append(rbm_layer)
self.log_layer = LogisticRegression(
input=self.sigmoid_layers[-1].sample_h_given_v(), label=self.y, n_in=hidden_layer_sizes[-1], n_out=n_outs
)
self.finetune_cost = self.log_layer.negative_log_likelihood()
class DBN(object):
def __init__(self, input=None, label=None, n_ins=2, hidden_layer_sizes=[3, 3], n_outs=2, numpy_rng=None):
self.x = input
self.y = label
self.sigmoid_layers = []
self.rbm_layers = []
self.n_layers = len(hidden_layer_sizes)
if numpy_rng is None:
numpy_rng = numpy.random.RandomState(1234)
assert self.n_layers > 0
# construct multi-layer
for i in xrange(self.n_layers):
# layer input size
if i == 0:
input_size = n_ins
else:
input_size = hidden_layer_sizes[i - 1]
# layer input
if i == 0:
layer_input = self.x
else:
layer_input = self.sigmoid_layers[-1].sample_h_given_v()
# construct sigmoid_layers
sigmoid_layer = HiddenLayer(
input=layer_input, n_in=input_size, n_out=hidden_layer_sizes[i], numpy_rng=numpy_rng, activation=sigmoid
)
self.sigmoid_layers.append(sigmoid_layer)
# construct rbm_layers
rbm_layer = RBM(
input=layer_input,
n_visible=input_size,
n_hidden=hidden_layer_sizes[i],
W=sigmoid_layer.W,
hbias=sigmoid_layer.b,
)
self.rbm_layers.append(rbm_layer)
self.log_layer = LogisticRegression(
input=self.sigmoid_layers[-1].sample_h_given_v(), label=self.y, n_in=hidden_layer_sizes[-1], n_out=n_outs
)
self.finetune_cost = self.log_layer.negative_log_likelihood()
def pretrain(self, lr=0.1, k=1, epochs=100):
for i in xrange(self.n_layers):
if i == 0:
layer_input = self.x
else:
layer_input = self.sigmoid_layers[i - 1].sample_h_given_v(layer_input)
rbm = self.rbm_layers[i]
for epoch in xrange(epochs):
rbm.contrastive_divergence(lr=lr, k=k, input=layer_input)
# cost = rbm.get_reconstruction_cross_entropy()
# print cost
def finetune(self, lr=0.1, epochs=100):
layer_input = self.sigmoid_layers[-1].sample_h_given_v()
epoch = 0
done_looping = False
while (epoch < epochs) and (not done_looping):
self.log_layer.train(lr=lr, input=layer_input)
# self.finetune_cost = self.log_layer.negative_log_likelihood()
# print self.finetune_cost
lr *= 0.95
epoch += 1
def predict(self, x):
layer_input = x
for i in xrange(self.n_layers):
sigmoid_layer = self.sigmoid_layers[i]
layer_input = sigmoid_layer.output(input=layer_input)
out = self.log_layer.predict(layer_input)
return out