def build_model(self):
""" Define model components and variables """
self.create_placeholders()
self.initialize_networks()
## model variables and relations ##
# infernce #
self.y_ = dgm.forwardPassCatLogits(self.x,
self.qy_x,
self.n_hid,
self.nonlinearity,
self.bn,
scope='qy_x',
reuse=False)
self.qz_in = tf.concat([self.x, self.y], axis=-1)
self.qz_mean, self.qz_lv, self.z_ = dgm.samplePassGauss(
self.qz_in,
self.qz_xy,
self.n_hid,
self.nonlinearity,
self.bn,
scope='qz_xy',
reuse=False)
# generative #
self.z_prior = tf.random_normal([100, self.n_z])
if self.x_dist == 'Gaussian':
self.px_mean, self.px_lv, self.x_ = dgm.samplePassGauss(
self.z_prior,
self.px_z,
self.n_hid,
self.nonlinearity,
self.bn,
scope='px_z',
reuse=False)
elif self.x_dist == 'Bernoulli':
self.x_ = dgm.forwardPassBernoulli(self.z_prior,
self.px_z,
self.n_hid,
self.nonlinearity,
self.bn,
scope='px_z',
reuse=False)
self.py_in = tf.concat([self.x_, self.z_prior], axis=-1)
self.py_ = dgm.forwardPassCat(self.py_in,
self.py_xz,
self.n_hid,
self.nonlinearity,
self.bn,
scope='py_xz',
reuse=False)
self.predictions = self.predict(self.x)
def build_model(self):
""" Define model components and variables """
self.create_placeholders()
self.initialize_networks()
## model variables and relations ##
# infernce #
self.qc_mean, self.qc_lv, self.c_ = dgm.samplePassStatistic(self.x, self.qc_x, self.n_hid, self.nonlinearity, self.bn, self.mc_samples, scope='qc_x', reuse=False)
self.c_ = tf.reshape(self.c_, [-1, self.n_c])
self.qz_in = tf.concat([self.x, tf.tile(self.c_, [tf.shape(self.x)[0], 1])], axis=-1)
self.qz_mean, self.qz_lv, self.qz_ = dgm.samplePassGauss(self.qz_in, self.qz_xc, self.n_hid, self.nonlinearity, self.bn, scope='qz_xc', reuse=False)
# generative #
self.c_prior = tf.random_normal([1, self.n_c])
self.pz_mean, self.pz_lv, self.pz_ = self.sample_pz(self.c_prior, 200, reuse=False)
self.pz_ = tf.reshape(self.pz_, [-1, self.n_z])
if self.x_dist == 'Gaussian':
self.px_mean, self.px_lv, self.px_ = dgm.samplePassGauss(self.pz_, self.px_z, self.n_hid, self.nonlinearity, self.bn, scope='px_z', reuse=False)
elif self.x_dist == 'Bernoulli':
self.px_ = dgm.forwardPassBernoulli(self.pz_, self.px_z, self.n_hid, self.nonlinearity, self.bn, scope='px_z', reuse=False)
def build_model(self):
""" Define model components and variables """
self.create_placeholders()
self.initialize_networks()
## model variables and relations ##
# inference #
self.y_ = dgm.forwardPassCatLogits(self.x, self.qy_x, self.n_hid, self.nonlinearity, self.bn, scope='qy_x', reuse=False)
self.qz_in = tf.concat([self.x, self.y], axis=-1)
self.qz_mean, self.qz_lv, self.z_ = dgm.samplePassGauss(self.qz_in, self.qz_xy, self.n_hid, self.nonlinearity, self.bn, scope='qz_xy', reuse=False)
# generative #
self.z_prior = tf.random_normal([tf.shape(self.y)[0], self.n_z])
self.px_in = tf.concat([self.y, self.z_prior], axis=-1)
if self.x_dist == 'Gaussian':
self.px_mean, self.px_lv, self.x_ = dgm.samplePassGauss(self.px_in, self.px_yz, self.n_hid, self.nonlinearity, self.bn, scope='px_yz', reuse=False)
self.x_ = tf.reshape(self.x_, [-1, self.n_x])
elif self.x_dist == 'Bernoulli':
self.x_ = dgm.forwardPassBernoulli(self.px_in, self.px_yz, self.n_hid, self.nonlinearity, self.bn, scope='px_yz', reuse=False)
self.W = bnn.sampleCatBNN(self.py_x, self.n_hid)
self.py = dgm.forwardPassCat(self.x_, self.W, self.n_hid, self.nonlinearity, self.bn, scope='py_x', reuse=False)
self.predictions = self.predict(self.x, n_samps=50, training=False)