def __init__(self, n_visible, n_hidden):
super(LearntPrecisionGaussianBinaryRBM, self).__init__()
# data shape
self.n_visible = n_visible
self.n_hidden = n_hidden
# units
self.v = units.LearntPrecisionGaussianUnits(self, name='v') # visibles
self.h = units.BinaryUnits(self, name='h') # hiddens
# parameters
self.Wm = parameters.ProdParameters(self, [self.v, self.h],
theano.shared(
value=self._initial_W(),
name='Wm'),
name='Wm') # weights
self.Wp = parameters.ProdParameters(
self, [self.v.precision_units, self.h],
theano.shared(value=-np.abs(self._initial_W()) / 1000, name='Wp'),
name='Wp') # weights
self.bvm = parameters.BiasParameters(
self,
self.v,
theano.shared(value=self._initial_bias(self.n_visible),
name='bvm'),
name='bvm') # visible bias
self.bvp = parameters.BiasParameters(
self,
self.v.precision_units,
theano.shared(value=self._initial_bias(self.n_visible),
name='bvp'),
name='bvp') # precision bias
self.bh = parameters.BiasParameters(
self,
self.h,
theano.shared(value=self._initial_bias(self.n_hidden), name='bh'),
name='bh') # hidden bias
def __init__(self, n_visible, n_hidden_mean, n_hidden_precision):
super(LearntPrecisionSeparateGaussianBinaryRBM, self).__init__()
# data shape
self.n_visible = n_visible
self.n_hidden_mean = n_hidden_mean
self.n_hidden_precision = n_hidden_precision
# units
self.v = units.LearntPrecisionGaussianUnits(self, name='v') # visibles
self.hm = units.BinaryUnits(self, name='hm') # hiddens for mean
self.hp = units.BinaryUnits(self, name='hp') # hiddens for precision
# parameters
self.Wm = parameters.ProdParameters(
self, [self.v, self.hm],
theano.shared(value=self._initial_W(self.n_visible,
self.n_hidden_mean),
name='Wm'),
name='Wm') # weights
self.Wp = parameters.ProdParameters(
self, [self.v.precision_units, self.hp],
theano.shared(value=-np.abs(
self._initial_W(self.n_visible, self.n_hidden_precision)) /
1000,
name='Wp'),
name='Wp') # weights
self.bvm = parameters.BiasParameters(
self,
self.v,
theano.shared(value=self._initial_bias(self.n_visible),
name='bvm'),
name='bvm') # visible bias
self.bvp = parameters.BiasParameters(
self,
self.v.precision_units,
theano.shared(value=self._initial_bias(self.n_visible),
name='bvp'),
name='bvp') # precision bias
self.bhm = parameters.BiasParameters(
self,
self.hm,
theano.shared(value=self._initial_bias(self.n_hidden_mean),
name='bhm'),
name='bhm') # hidden bias for mean
self.bhp = parameters.BiasParameters(
self,
self.hp,
theano.shared(value=self._initial_bias(self.n_hidden_precision) +
1.0,
name='bhp'),
name='bhp') # hidden bias for precision
def __init__(self, n_visible, n_hidden, n_context):
super(BinaryBinaryCRBM, self).__init__(n_visible, n_hidden)
# data shape
self.n_context = n_context
# units
self.x = units.Units(self, name='x') # context
# parameters
self.A = parameters.ProdParameters(
self, [self.x, self.v],
theano.shared(value=self._initial_A(), name='A'),
name='A') # context-to-visible weights
self.B = parameters.ProdParameters(
self, [self.x, self.h],
theano.shared(value=self._initial_B(), name='B'),
name='B') # context-to-hidden weights
def __init__(self, n_visible, n_hidden):
super(GaussianBinaryRBM, self).__init__()
# data shape
self.n_visible = n_visible
self.n_hidden = n_hidden
# units
self.v = units.GaussianUnits(self, name='v') # visibles
self.h = units.BinaryUnits(self, name='h') # hiddens
# parameters
parameters.FixedBiasParameters(self, self.v.precision_units)
self.W = parameters.ProdParameters(self, [self.v, self.h],
theano.shared(
value=self._initial_W(),
name='W'),
name='W') # weights
self.bv = parameters.BiasParameters(self,
self.v,
theano.shared(
value=self._initial_bv(),
name='bv'),
name='bv') # visible bias
self.bh = parameters.BiasParameters(self,
self.h,
theano.shared(
value=self._initial_bh(),
name='bh'),
name='bh') # hidden bias
def __init__(self, n_visible, n_hidden):
super(TruncExpBinaryRBM, self).__init__()
# data shape
self.n_visible = n_visible
self.n_hidden = n_hidden
# units
self.v = units.TruncatedExponentialUnits(self, name='v') # visibles
self.h = units.BinaryUnits(self, name='h') # hiddens
# parameters
self.W = parameters.ProdParameters(self, [self.v, self.h],
theano.shared(
value=self._initial_W(),
name='W'),
name='W') # weights
self.bv = parameters.BiasParameters(self,
self.v,
theano.shared(
value=self._initial_bv(),
name='bv'),
name='bv') # visible bias
self.bh = parameters.BiasParameters(self,
self.h,
theano.shared(
value=self._initial_bh(),
name='bh'),
name='bh') # hidden bias
def __init__(self, n_visible, n_hidden, n_factors):
super(FactoredBinaryBinaryRBM, self).__init__()
# data shape
self.n_visible = n_visible
self.n_hidden = n_hidden
self.n_factors = n_factors
# units
self.v = units.BinaryUnits(self, name='v') # visibles
self.h = units.BinaryUnits(self, name='h') # hiddens
# parameters
Wv = theano.shared(value=self._initial_W(self.n_visible,
self.n_factors),
name='Wv')
Wh = theano.shared(value=self._initial_W(self.n_hidden,
self.n_factors),
name='Wh')
self.F = factors.Factor(self, name='F') # factor
self.Wv = parameters.ProdParameters(self.F, [self.v, self.F],
Wv,
name='Wv')
self.Wh = parameters.ProdParameters(self.F, [self.h, self.F],
Wh,
name='Wh')
self.F.initialize()
self.bv = parameters.BiasParameters(self,
self.v,
theano.shared(
value=self._initial_bv(),
name='bv'),
name='bv') # visible bias
self.bh = parameters.BiasParameters(self,
self.h,
theano.shared(
value=self._initial_bh(),
name='bh'),
name='bh') # hidden bias
# This example shows how the FIOTRBM model from "Facial Expression Transfer with
# Input-Output Temporal Restricted Boltzmann Machines" by Zeiler et al. (NIPS
# 2011) can be recreated in Morb.
rbm = base.RBM()
rbm.v = units.GaussianUnits(rbm) # output (visibles)
rbm.h = units.BinaryUnits(rbm) # latent (hiddens)
rbm.s = units.Units(rbm) # input (context)
rbm.vp = units.Units(rbm) # output history (context)
initial_A = ...
initial_B = ...
initial_bv = ...
initial_bh = ...
initial_Wv = ...
initial_Wh = ...
initial_Ws = ...
parameters.FixedBiasParameters(
rbm, rbm.v.precision_units) # add precision term to the energy function
rbm.A = parameters.ProdParameters(
rbm, [rbm.vp, rbm.v],
initial_A) # weights from past output to current output
rbm.B = parameters.ProdParameters(
rbm, [rbm.vp, rbm.h], initial_B) # weights from past output to hiddens
rbm.bv = parameters.BiasParameters(rbm, rbm.v, initial_bv) # visible bias
rbm.bh = parameters.BiasParameters(rbm, rbm.h, initial_bh) # hidden bias
rbm.W = parameters.ThirdOrderFactoredParameters(
rbm, [rbm.v, rbm.h, rbm.s],
[initial_Wv, initial_Wh, initial_Ws]) # factored third order weights
initial_bh = np.zeros(n_hidden, dtype=theano.config.floatX)
rbm = morb.base.RBM()
rbm.v = units.BinaryUnits(rbm, name='v') # visibles
rbm.h = units.BinaryUnits(rbm, name='h') # hiddens
rbm.x = units.Units(rbm, name='x') # context
Wv = theano.shared(value=initial_W(n_visible, n_factors), name='Wv')
Wh = theano.shared(value=initial_W(n_hidden, n_factors), name='Wh')
# Wx = theano.shared(value=initial_W(n_context, n_factors), name='Wx')
Wx = Wv # parameter tying
# rbm.W = parameters.ThirdOrderFactoredParameters(rbm, [rbm.v, rbm.h, rbm.x], [Wv, Wh, Wx], name='W') # weights
rbm.F = factors.Factor(rbm, name='F')
# IMPORTANT: the following parameters instances are associated with the FACTOR rbm.F, and not with the RBM itself.
rbm.Wv = parameters.ProdParameters(rbm.F, [rbm.v, rbm.F], Wv, name='Wv')
rbm.Wh = parameters.ProdParameters(rbm.F, [rbm.h, rbm.F], Wh, name='Wh')
rbm.Wx = parameters.ProdParameters(rbm.F, [rbm.x, rbm.F], Wx, name='Wx')
rbm.F.initialize() # done adding parameters to rbm.F
rbm.bv = parameters.BiasParameters(rbm,
rbm.v,
theano.shared(value=initial_bv, name='bv'),
name='bv') # visible bias
rbm.bh = parameters.BiasParameters(rbm,
rbm.h,
theano.shared(value=initial_bh, name='bh'),
name='bh') # hidden bias
initial_vmap = {rbm.v: T.matrix('v'), rbm.x: T.matrix('x')}