Пример #1
0
 def cost(self, readouts, outputs):
     mu, sigma, coeff = self.components(readouts)
     #ipdb.set_trace()
     return GMM(outputs, mu, sigma, coeff)
Пример #2
0
bricks = [mlp_x, transition, mlp_gmm]

for brick in bricks:
    brick.weights_init = IsotropicGaussian(0.01)
    brick.biases_init = Constant(0.)
    brick.initialize()

##############
# Test model
##############

x_g = mlp_x.apply(x)
h = transition.apply(x_g)
mu, sigma, coeff = mlp_gmm.apply(h[-2])

cost = GMM(y, mu, sigma, coeff)
cost = cost.mean()
cost.name = 'sequence_log_likelihood'

cg = ComputationGraph(cost)
model = Model(cost)

#################
# Algorithm
#################

n_batches = 139 * 16

algorithm = GradientDescent(cost=cost,
                            parameters=cg.parameters,
                            step_rule=CompositeRule(
Пример #3
0
##############
# Test model
##############

x_g = mlp_x.apply(x)
h = transition.apply(x_g)
mu, sigma, coeff = mlp_gmm.apply(h[-2])

#from theano import function
#x_tr, x_mask_tr, y_tr = next(data_stream.get_epoch_iterator())
#print function([x], x_g)(x_tr).shape
#print function([x], h)(x_tr)[-2].shape
#print function([x], mu)(x_tr).shape

from play.utils import GMM
cost = GMM(y, mu, sigma, coeff)
cost = cost*x_mask
cost = cost.sum()/x_mask.sum()
cost.name = 'sequence_log_likelihood'

cg = ComputationGraph(cost)
model = Model(cost)

#ipdb.set_trace()
#x_tr, x_mask_tr, y_tr = next(data_stream.get_epoch_iterator())
#print function([x, x_mask, y], cost)(x_tr, x_mask_tr, y_tr)

#################
# Algorithm
#################
Пример #4
0
bricks = [mlp_x, transition, mlp_gmm]

for brick in bricks:
    brick.weights_init = IsotropicGaussian(0.01)
    brick.biases_init = Constant(0.)
    brick.initialize()

##############
# Test model
##############

x_g = mlp_x.apply(x)
h = transition.apply(x_g)
mu, sigma, coeff = mlp_gmm.apply(h[-2])

cost = GMM(y, mu, sigma, coeff)
cost = cost.mean()
cost.name = 'sequence_log_likelihood'

cg = ComputationGraph(cost)
model = Model(cost)

#################
# Algorithm
#################

n_batches = 139*16

algorithm = GradientDescent(
    cost=cost, parameters=cg.parameters,
    step_rule=CompositeRule([StepClipping(10.0), Adam(lr)]))