def sample(self, n=1):
W1 = self.W1.get_value()
b1 = self.b1.get_value()
Wflags = self.Wflags.get_value()
if self.n_layers > 1:
Ws = self.Ws.get_value()
bs = self.bs.get_value()
V = self.V.get_value()
c = self.c.get_value()
nl = self.parameters["nonlinearity"].get_numpy_f()
samples = np.zeros((self.n_visible, n))
for s in xrange(n):
# Sample an ordering
ordering = self.orderings[np.random.randint(len(self.orderings))]
a = np.zeros((self.n_hidden, )) # H
input_mask_contribution = np.zeros((self.n_hidden))
for j in xrange(self.n_visible):
i = ordering[j]
h = nl(input_mask_contribution + a + b1)
for l in xrange(self.n_layers - 1):
h = nl(np.dot(h, Ws[l]) + bs[l])
t = np.dot(h, V[i]) + c[i]
p_xi_is_one = sigmoid(t) * 0.9999 + 0.0001 * 0.5 # B
input_mask_contribution += Wflags[i]
a += np.dot(samples[i, s][np.newaxis, np.newaxis],
W1[i][np.newaxis, :])
samples[i, s] = np.random.random() < p_xi_is_one
return samples
def sample(self, n=1):
W1 = self.W1.get_value()
b1 = self.b1.get_value()
Wflags = self.Wflags.get_value()
if self.n_layers > 1:
Ws = self.Ws.get_value()
bs = self.bs.get_value()
V = self.V.get_value()
c = self.c.get_value()
nl = self.parameters["nonlinearity"].get_numpy_f()
samples = np.zeros((self.n_visible, n))
for s in xrange(n):
# Sample an ordering
ordering = self.orderings[np.random.randint(len(self.orderings))]
a = np.zeros((self.n_hidden,)) # H
input_mask_contribution = np.zeros((self.n_hidden))
for j in xrange(self.n_visible):
i = ordering[j]
h = nl(input_mask_contribution + a + b1)
for l in xrange(self.n_layers - 1):
h = nl(np.dot(h, Ws[l]) + bs[l])
t = np.dot(h, V[i]) + c[i]
p_xi_is_one = sigmoid(t) * 0.9999 + 0.0001 * 0.5 # B
input_mask_contribution += Wflags[i]
a += np.dot(samples[i, s][np.newaxis, np.newaxis], W1[i][np.newaxis, :])
samples[i, s] = np.random.random() < p_xi_is_one
return samples
def logdensity(self, x):
""" x is a matrix of column datapoints (VxB) V = n_visible, B = batch size """
B = x.shape[1]
nl = self.parameters["nonlinearity"].get_numpy_f()
lp = np.zeros((B, self.n_orderings))
W1 = self.W1.get_value()
b1 = self.b1.get_value()
Wflags = self.Wflags.get_value()
if self.n_layers > 1:
Ws = self.Ws.get_value()
bs = self.bs.get_value()
V = self.V.get_value()
c = self.c.get_value()
for o_index, o in enumerate(self.orderings):
a = np.zeros((B, self.n_hidden))
input_mask_contribution = np.zeros((B, self.n_hidden))
for j in xrange(self.n_visible):
i = o[j]
x_i = x[i]
h = nl(input_mask_contribution + a + b1)
for l in xrange(self.n_layers - 1):
h = nl(np.dot(h, Ws[l]) + bs[l])
t = np.dot(h, V[i]) + c[i]
p_xi_is_one = sigmoid(t) * 0.9999 + 0.0001 * 0.5
lp[:, o_index] += x_i * np.log(p_xi_is_one) + (
1 - x_i) * np.log(1 - p_xi_is_one)
a += np.dot(x[i][:, np.newaxis], W1[i][np.newaxis, :])
input_mask_contribution += Wflags[i]
return logsumexp(lp + np.log(1 / self.n_orderings))
def logdensity(self, x):
""" x is a matrix of column datapoints (VxB) V = n_visible, B = batch size """
B = x.shape[1]
nl = self.parameters["nonlinearity"].get_numpy_f()
lp = np.zeros((B, self.n_orderings))
W1 = self.W1.get_value()
b1 = self.b1.get_value()
Wflags = self.Wflags.get_value()
if self.n_layers > 1:
Ws = self.Ws.get_value()
bs = self.bs.get_value()
V = self.V.get_value()
c = self.c.get_value()
for o_index, o in enumerate(self.orderings):
a = np.zeros((B, self.n_hidden))
input_mask_contribution = np.zeros((B, self.n_hidden))
for j in xrange(self.n_visible):
i = o[j]
x_i = x[i]
h = nl(input_mask_contribution + a + b1)
for l in xrange(self.n_layers - 1):
h = nl(np.dot(h, Ws[l]) + bs[l])
t = np.dot(h, V[i]) + c[i]
p_xi_is_one = sigmoid(t) * 0.9999 + 0.0001 * 0.5
lp[:, o_index] += x_i * np.log(p_xi_is_one) + (1 - x_i) * np.log(1 - p_xi_is_one)
a += np.dot(x[i][:, np.newaxis], W1[i][np.newaxis, :])
input_mask_contribution += Wflags[i]
return logsumexp(lp + np.log(1 / self.n_orderings))
