def _encoder(self, x, is_training=None):
net = self.arch['encoder']
for i, (o, k, s) in enumerate(zip(net['output'], net['kernel'], net['stride'])):
x = conv2d_nchw_layernorm(
x, o, k, s, lrelu,
name='Conv2d-{}'.format(i)
)
x = slim.flatten(x)
z_mu = tf.layers.dense(x, self.arch['z_dim'])
z_lv = tf.layers.dense(x, self.arch['z_dim'])
return z_mu, z_lv
def _encoder(self, x, is_training=None):
net = self.arch['encoder']
for i, (o, k, s) in enumerate(zip(net['output'], net['kernel'], net['stride'])):
x = conv2d_nchw_layernorm(
x, o, k, s, lrelu,
name='Conv2d-{}'.format(i)
)
x = slim.flatten(x)
z_mu = tf.layers.dense(x, self.arch['z_dim'])
z_lv = tf.layers.dense(x, self.arch['z_dim'])
return z_mu, z_lv
def _discriminator(self, x, is_training=None):
net = self.arch['discriminator']
for i, (o, k, s) in enumerate(
zip(net['output'], net['kernel'], net['stride'])):
x = conv2d_nchw_layernorm(x,
o,
k,
s,
lrelu,
name='Conv2d-{}'.format(i))
x = slim.flatten(x)
d = tf.layers.dense(x, 1)
return d
def _encoder(self, x, net):
x = tf.transpose(x, perm=[0, 3, 2, 1]) # [N, d, n_frames, 1]
for i, (o, k, s) in enumerate(zip(net['output'], net['kernel'], net['stride'])):
x = conv2d_nchw_layernorm(
x, o, k, s, lrelu,
name='Conv-{}'.format(i)
)
# carefully design the architecture so that now x has shape [N, C, n_frames, 1]
batch_size, c, n_frames, w = x.get_shape().as_list()
x = tf.transpose(x, perm=[0, 2, 1, 3]) # [N, n_frames, C, 1]
x = tf.squeeze(x, axis=[-1]) # [N, n_frames, C]
z_mu = tf.layers.dense(x, self.arch['z_dim'], name='Dense-mu') # [N, n_frames, z_dim]
z_lv = tf.layers.dense(x, self.arch['z_dim'], name='Dense-lv') # [N, n_frames, z_dim]
return z_mu, z_lv
def _discriminator(self, x, net):
x = tf.transpose(x, perm=[0, 3, 2, 1]) # [N, d, n_frames, 1]
for i, (o, k, s) in enumerate(zip(net['output'], net['kernel'], net['stride'])):
x = conv2d_nchw_layernorm(
x, o, k, s, lrelu,
name='Conv-{}'.format(i)
)
# carefully design the architecture so that now x has shape [N, C, n_frames, 1]
batch_size, c, n_frames, w = x.get_shape().as_list()
x = tf.transpose(x, perm=[0, 2, 1, 3]) # [N, n_frames, C, 1]
x = tf.squeeze(x, axis=[-1]) # [N, n_frames, C]
x = tf.layers.dense(x, 1) # [N, n_frames, 1]
return tf.reduce_mean(x, axis=1) #[N, 1]
def _encoder(self, x, is_training=None):
net = self.arch['encoder']
print "x shape:", x.get_shape().as_list()
#time.sleep(100)
for i, (o, k, s) in enumerate(
zip(net['output'], net['kernel'], net['stride'])):
x = conv2d_nchw_layernorm(x,
o,
k,
s,
lrelu,
name='Conv2d-{}'.format(i))
print("ConvT-LN{}, shape:".format(i), x.get_shape().as_list())
print "x shape:", x.get_shape().as_list()
x = slim.flatten(x)
print "x shape:", x.get_shape().as_list()
#time.sleep(100)
z_mu = tf.layers.dense(x, self.arch['z_dim'])
z_lv = tf.layers.dense(x, self.arch['z_dim'])
print "z_mu:", z_mu.get_shape().as_list()
#time.sleep(100)
return z_mu, z_lv