def get_nade_k_LL_ensemble_theano(self, k, n_orderings):
# 1/M sum_M log (sum_K 1/k p(x_m | o_k))
# only support matrix x with first dim 1
ordering = T.imatrix('ordering')
# (O,D)
ordering.tag.test_value = numpy.repeat(numpy.arange(
self.n_visible)[numpy.newaxis, :],
n_orderings,
axis=0).astype('int32')
# (O,D)
#input_mask_init = T.fmatrix('input_mask')
#input_mask_init.tag.test_value = numpy.zeros((10,self.n_visible),dtype=floatX)
input_mask_init = constantX(
numpy.zeros((n_orderings, self.n_visible), dtype=floatX))
x = T.fmatrix('samples')
x.tag.test_value = numpy.random.binomial(
n=1, p=0.5, size=(1, self.n_visible)).astype(floatX)
def compute_LL_one_column(
this_bit_vector, # vector
input_mask, # [1, 0, 0 ,1, 0, 0, 1 ] with 1 indicates bits already sampled
x, # testset minibatches
W1,
Wflags,
c):
one = theano.tensor.constant(1, dtype=floatX)
# a list of (k,O,D)
x_ = T.addbroadcast(x, 0)
means = self.get_nade_k_mean_field(x_, input_mask, k)
# use the mean coming from the last step of mean field
# (O,D)
use_mean = means[-1]
mean_column = use_mean[T.arange(use_mean.shape[0]), \
this_bit_vector]*constantX(0.9999)+ \
constantX(0.0001*0.5)
x_column = x.flatten()[this_bit_vector]
LL = x_column*T.log(mean_column) + \
(constantX(1)-x_column)*T.log(constantX(1)-mean_column)
# set the new input mask: (O,D)
input_mask = T.set_subtensor(
input_mask[T.arange(input_mask.shape[0]), this_bit_vector],
one)
return LL, input_mask
[LLs, input_mask], updates = theano.scan(
fn=compute_LL_one_column,
outputs_info=[None, input_mask_init],
sequences=[ordering.T],
non_sequences=[x, self.W1, self.Wflags, self.c],
)
# LLs: (D,O)
LL = utils.log_sum_exp_theano(LLs.sum(axis=0), axis=-1) - T.log(
ordering.shape[1])
f = theano.function(inputs=[x, ordering],
outputs=LL,
updates=updates,
name='LL_on_one_example_fn')
return f
def get_nade_k_LL_ensemble_theano_minibatch(self, k, n_orderings):
# As a mixture model, Equ (18) in the paper
ordering = T.imatrix('ordering')
# (O,D)
ordering.tag.test_value = numpy.repeat(numpy.arange(
self.n_visible)[numpy.newaxis, :],
n_orderings,
axis=0).astype('int32')
# (O,D)
input_mask_init = constantX(
numpy.zeros((n_orderings, self.n_visible), dtype=floatX))
x = T.fmatrix('samples')
x.tag.test_value = numpy.random.binomial(
n=1, p=0.5,
size=(self.minibatch_size, self.n_visible)).astype(floatX)
x_ = x.dimshuffle(0, 'x', 1)
def compute_LL_one_column(
this_bit_vector, # vector
input_mask, # [1, 0, 0 ,1, 0, 0, 1 ] with 1 indicates bits already sampled
x,
x_, # testset minibatches
W1,
Wflags,
c):
one = theano.tensor.constant(1, dtype=floatX)
#means = self.get_nade_k_mean_field(x_, input_mask.dimshuffle('x',0,1), k)
means = self.get_nade_k_mean_field(x_, input_mask, k)
# use the mean coming from the last step of mean field
# (M,O,D)
use_mean = means[-1]
# (M,O)
use_mean_shape = use_mean.shape
use_mean = use_mean.reshape(
[use_mean_shape[0], use_mean_shape[1] * use_mean_shape[2]])
idx = use_mean_shape[2] * T.arange(
use_mean_shape[1]) + this_bit_vector
mean_column = use_mean[:, idx] * constantX(0.9999) + constantX(
0.0001 * 0.5)
#mean_column = use_mean[:,T.arange(use_mean.shape[1]), \
# this_bit_vector]*constantX(0.9999)+ \
# constantX(0.0001*0.5)
x_column = x_.reshape([x_.shape[0], x_.shape[2]])[:,
this_bit_vector]
# (M,O)
LL = x_column*T.log(mean_column) + \
(constantX(1)-x_column)*T.log(constantX(1)-mean_column)
# set the new input mask: (O,D)
input_mask_shape = input_mask.shape
input_mask = input_mask.flatten()
idx = input_mask_shape[1] * T.arange(
input_mask_shape[0]) + this_bit_vector
input_mask = T.set_subtensor(input_mask[idx], one)
input_mask = input_mask.reshape(input_mask_shape)
#input_mask = T.set_subtensor(input_mask[T.arange(input_mask.shape[0]),
# this_bit_vector],one)
return LL, input_mask
[LLs, input_mask], updates = theano.scan(
fn=compute_LL_one_column,
outputs_info=[None, input_mask_init],
sequences=[ordering.T],
non_sequences=[x, x_, self.W1, self.Wflags, self.c],
)
# LLs: (D,M,O)
LL = utils.log_sum_exp_theano(LLs.sum(axis=0), axis=-1) - T.log(
ordering.shape[0])
LL_orders = LLs.sum(axis=0)
f = theano.function(inputs=[x, ordering],
outputs=[LL, LL_orders],
updates=updates,
name='LL_on_one_example_fn')
return f
