def generator(observed, n, n_z, is_training):
with zs.BayesianNet(observed=observed) as generator:
z_min = -tf.ones([n, n_z])
z_max = tf.ones([n, n_z])
z = zs.Uniform('z', z_min, z_max)
lx_z = tf.reshape(z, [-1, 1, 1, n_z])
ngf = 32
lx_z = tf.layers.conv2d_transpose(lx_z, ngf * 4, 3, use_bias=False)
lx_z = tf.layers.batch_normalization(lx_z,
training=is_training,
scale=False)
lx_z = tf.nn.relu(lx_z)
lx_z = tf.layers.conv2d_transpose(lx_z, ngf * 2, 5, use_bias=False)
lx_z = tf.layers.batch_normalization(lx_z,
training=is_training,
scale=False)
lx_z = tf.nn.relu(lx_z)
lx_z = tf.layers.conv2d_transpose(lx_z,
ngf,
5,
strides=(2, 2),
padding='same',
use_bias=False)
lx_z = tf.layers.batch_normalization(lx_z,
training=is_training,
scale=False)
lx_z = tf.nn.relu(lx_z)
lx_z = tf.layers.conv2d_transpose(lx_z,
1,
5,
strides=(2, 2),
padding='same',
activation=tf.sigmoid)
return generator, lx_z
def generator(observed, n, n_z, is_training):
with zs.BayesianNet(observed=observed) as generator:
normalizer_params = {
'is_training': is_training,
'updates_collections': None
}
ngf = 64
z_min = -tf.ones([n, n_z])
z_max = tf.ones([n, n_z])
z = zs.Uniform('z', z_min, z_max)
lx_z = layers.fully_connected(z,
num_outputs=ngf * 8 * 4 * 4,
normalizer_fn=layers.batch_norm,
normalizer_params=normalizer_params)
lx_z = tf.reshape(lx_z, [-1, 4, 4, ngf * 8])
lx_z = layers.conv2d_transpose(lx_z,
ngf * 4,
5,
stride=2,
normalizer_fn=layers.batch_norm,
normalizer_params=normalizer_params)
lx_z = layers.conv2d_transpose(lx_z,
ngf * 2,
5,
stride=2,
normalizer_fn=layers.batch_norm,
normalizer_params=normalizer_params)
lx_z = layers.conv2d_transpose(lx_z,
3,
5,
stride=2,
activation_fn=tf.nn.sigmoid)
return generator, lx_z
def generator(observed, n, n_z, is_training):
with zs.BayesianNet(observed=observed) as generator:
normalizer_params = {
'is_training': is_training,
'updates_collections': None
}
z_min = -tf.ones([n, n_z])
z_max = tf.ones([n, n_z])
z = zs.Uniform('z', z_min, z_max)
lx_z = tf.reshape(z, [-1, 1, 1, n_z])
ngf = 32
lx_z = layers.conv2d_transpose(lx_z,
ngf * 4,
3,
padding='VALID',
normalizer_fn=layers.batch_norm,
normalizer_params=normalizer_params)
lx_z = layers.conv2d_transpose(lx_z,
ngf * 2,
5,
padding='VALID',
normalizer_fn=layers.batch_norm,
normalizer_params=normalizer_params)
lx_z = layers.conv2d_transpose(lx_z,
ngf,
5,
stride=2,
normalizer_fn=layers.batch_norm,
normalizer_params=normalizer_params)
lx_z = layers.conv2d_transpose(lx_z,
1,
5,
stride=2,
activation_fn=tf.nn.sigmoid)
return generator, lx_z