def generator(self, z, c, reuse=None, is_train=True):
"""
:param z: 139 z-noise
:param c: 10 categories * 10 dimensions
:param reuse: re-usable
:param is_train: trainable
:return: prob
"""
with tf.variable_scope("generator", reuse=reuse):
x = tf.concat([z, c], axis=1) # (-1, 128 + 1 + 10)
x = t.dense(x, 2 * 2 * 512, name='gen-fc-1')
x = t.batch_norm(x, is_train=is_train, name='gen-bn-1')
x = tf.nn.relu(x)
x = tf.reshape(x, (-1, 2, 2, 512))
x = t.deconv2d(x, self.gf_dim * 8, 4, 2, name='gen-deconv2d-1')
x = t.batch_norm(x, is_train=is_train, name='gen-bn-2')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.gf_dim * 4, 4, 2, name='gen-deconv2d-2')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.gf_dim * 2, 4, 2, name='gen-deconv2d-3')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.gf_dim * 1, 4, 2, name='gen-deconv2d-4')
x = tf.nn.relu(x)
x = t.deconv2d(x, 3, 4, 2, name='gen-deconv2d-5')
x = tf.nn.tanh(x)
return x
def generator(self, z, y, reuse=None, is_train=True):
"""
# Following a G Network, CiFar-like-hood, referred in the paper
:param z: noise
:param y: image label
:param reuse: re-usable
:param is_train: trainable
:return: prob
"""
with tf.variable_scope("generator", reuse=reuse):
x = tf.concat([z, y], axis=1) # (-1, 110)
x = t.dense(x, self.gf_dim, name='gen-fc-1')
x = tf.nn.relu(x)
x = tf.reshape(x, (-1, 4, 4, 24))
for i in range(1, 3):
x = t.deconv2d(x,
self.gf_dim // (2**i),
5,
2,
name='gen-deconv2d-%d' % (i + 1))
x = t.batch_norm(x,
is_train=is_train,
reuse=reuse,
name="gen-bn-%d" % i)
x = tf.nn.relu(x)
x = t.deconv2d(x, self.channel, 5, 2, name='gen-deconv2d-4')
x = tf.nn.tanh(x) # scaling to [-1, 1]
return x
def generator(self, z, y=None, share_params=False, reuse=False, training=True, name=""):
if y is None:
x = tf.concat([z, y], axis=1)
else:
x = z
x = tf.layers.flatten(x)
x = tf.layers.dense(x, self.fc_unit, reuse=share_params, name='gen-dense-0')
x = t.prelu(x, reuse=share_params, name='gen-prelu-0')
x = tf.layers.dense(x, self.gf_dim * 8 * 7 * 7, reuse=share_params, name='gen-dense-1')
x = t.batch_norm(x, reuse=share_params, is_train=training, name='gen-bn-0')
x = t.prelu(x, reuse=share_params, name='gen-prelu-1')
x = tf.reshape(x, (self.batch_size, 7, 7, self.gf_dim * 8))
# x = deconv2d(x, f=self.gf_dim * 16, k=4, s=1, reuse=share_params, name='gen-deconv2d-0')
# x = batch_norm(x, reuse=share_params, training=training, name="gen-bn-0")
# x = prelu(x, reuse=share_params, name='gen-prelu-1')
x = t.deconv2d(x, f=self.gf_dim * 4, k=3, s=2, reuse=share_params, name='gen-deconv2d-1')
x = t.batch_norm(x, reuse=share_params, is_train=training, name="gen-bn-1")
x = t.prelu(x, reuse=share_params, name='gen-prelu-2')
x = t.deconv2d(x, f=self.gf_dim * 2, k=3, s=2, reuse=share_params, name='gen-deconv2d-2')
x = t.batch_norm(x, reuse=share_params, is_train=training, name="gen-bn-2")
x = t.prelu(x, reuse=share_params, name='gen-prelu-3')
with tf.variable_scope("generator-%s" % name, reuse=reuse):
x = t.deconv2d(x, f=self.channel, k=6, s=1, reuse=False, name='gen-' + name + '-deconv2d-3')
x = tf.nn.sigmoid(x, name='gen' + name + '-sigmoid-0')
return x
def generator(self, z, y=None, reuse=None, is_train=True):
"""
:param z: embeddings
:param y: labels
:param reuse: re-usable
:param is_train: en/disable batch_norm, default True
:return: prob
"""
with tf.variable_scope("generator", reuse=reuse):
if y:
raise NotImplemented("[-] Not Implemented Yet...")
x = t.dense(z, f=self.fc_unit, name='gen-fc-0')
x = tf.nn.leaky_relu(x)
x = tf.reshape(x, [-1, 8, 8, self.fc_unit // (8 * 8)])
for i in range(1, 4):
x = t.deconv2d(x, f=self.gf_dim * (2 ** i), name="gen-conv2d-%d" % i)
x = t.batch_norm(x, is_train=is_train)
x = tf.nn.leaky_relu(x)
x = t.deconv2d(x, f=3, s=1, name="gen-conv2d-4") # (-1, 64, 64, 3)
x = tf.sigmoid(x) # [0, 1]
return x
def generator(self, z, reuse=None, is_train=True):
"""
:param z: embeddings
:param reuse: re-usable
:param is_train: trainable
:return: prob
"""
with tf.variable_scope("generator", reuse=reuse):
x = tf.reshape(z, (-1, 1, 1, self.z_dim))
x = t.deconv2d(x,
self.df_dim * 8,
4,
1,
pad='VALID',
name='gen-deconv2d-1')
x = t.batch_norm(x, is_train=is_train, name='gen-bn-1')
x = tf.nn.relu(x)
for i in range(1, 4):
x = t.deconv2d(x,
self.df_dim * 8 // (2**i),
4,
2,
name='gen-deconv2d-%d' % (i + 1))
x = t.batch_norm(x,
is_train=is_train,
name='gen-bn-%d' % (i + 1))
x = tf.nn.relu(x)
x = t.deconv2d(x, self.channel, 4, 2, name='gen-deconv2d-5')
x = tf.nn.tanh(x)
return x
def generator(self, y, z, reuse=None, is_train=True):
"""
# Following a G Network, CiFar-like-hood, referred in the paper
:param y: image label
:param z: image noise
:param reuse: re-usable
:param is_train: trainable
:return: prob
"""
with tf.variable_scope("generator", reuse=reuse):
x = tf.concat([z, y], axis=1)
x = tf.layers.dense(x, self.gf_dim * 2, name='g-fc-0')
x = tf.nn.relu(x)
x = tf.layers.dense(x, self.gf_dim * 7 * 7, name='g-fc-1')
x = tf.nn.relu(x)
x = tf.reshape(x, [-1, 7, 7, self.gf_dim])
x = t.deconv2d(x, f=self.gf_dim // 2, k=5, s=2, name='g-deconv-1')
x = t.batch_norm(x, is_train=is_train)
x = tf.nn.relu(x)
x = t.deconv2d(x, f=1, k=5, s=2, name='g-deconv-2') # channel
x = tf.nn.sigmoid(x) # x = tf.nn.tanh(x)
return x
def generator(self, z, reuse=None, is_train=True):
"""
# referred architecture in the paper
: (1024)4c - (512)4c2s - (256)4c2s - (128)4c2s - (3)4c2s
:param z: embeddings
:param reuse: re-usable
:param is_train: trainable
:return: prob
"""
with tf.variable_scope("generator", reuse=reuse):
x = t.dense(z, self.gf_dim * 8 * 4 * 4, name='gen-fc-1')
x = tf.reshape(x, (-1, 4, 4, self.gf_dim * 8))
x = t.batch_norm(x, is_train=is_train, name='gen-bn-1')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.gf_dim * 4, 4, 2, name='gen-deconv2d-1')
x = t.batch_norm(x, is_train=is_train, name='gen-bn-2')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.gf_dim * 2, 4, 2, name='gen-deconv2d-2')
x = t.batch_norm(x, is_train=is_train, name='gen-bn-3')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.gf_dim * 1, 4, 2, name='gen-deconv2d-3')
x = t.batch_norm(x, is_train=is_train, name='gen-bn-4')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.channel, 4, 2, name='gen-deconv2d-4')
x = tf.nn.tanh(x)
return x
def generator(self, z, reuse=None):
with tf.variable_scope('generator', reuse=reuse):
x = t.dense(z, self.gf_dim * 4 * 4 * 4, name='gen-fc-1')
x = t.batch_norm(x, reuse=reuse, name='gen-bn-1')
x = tf.nn.relu(x)
x = tf.reshape(x, (-1, 4, 4, self.gf_dim * 4))
for i in range(1, 4):
x = t.deconv2d(x, self.gf_dim * 4 // (2 ** (i - 1)), 5, 2, name='gen-deconv2d-%d' % i)
x = t.batch_norm(x, reuse=reuse, name='gen-bn-%d' % (i + 1))
x = tf.nn.relu(x)
x = t.deconv2d(x, self.channel, 5, 1, name='gen-deconv2d-5')
x = tf.nn.tanh(x)
return x
def generator(self, z, y=None, share_params=False, reuse=False, name=""):
x = t.dense(z, self.fc_g_unit, reuse=share_params, name='gen-fc-1')
x = t.batch_norm(x, reuse=share_params, name='gen-bn-1')
x = t.prelu(x, reuse=share_params, name='gen-prelu-1')
x = t.dense(x,
self.gf_dim * 8 * 7 * 7,
reuse=share_params,
name='gen-fc-2')
x = t.batch_norm(x, reuse=share_params, name='gen-bn-2')
x = t.prelu(x, reuse=share_params, name='gen-prelu-2')
x = tf.reshape(x, (-1, 7, 7, self.gf_dim * 8))
for i in range(1, 3):
x = t.deconv2d(x,
f=self.gf_dim * 4 // i,
k=3,
s=2,
reuse=share_params,
name='gen-deconv2d-%d' % i)
x = t.batch_norm(x, reuse=share_params, name="gen-bn-%d" % (i + 2))
x = t.prelu(x, reuse=share_params, name='gen-prelu-%d' % (i + 2))
"""
x = z # tf.concat([z, y], axis=1)
loop = 5
for i in range(1, loop):
x = t.dense(x, self.fc_g_unit, reuse=share_params, name='gen-fc-%d' % i)
x = t.batch_norm(x, reuse=share_params, name='gen-bn-%d' % i)
x = t.prelu(x, reuse=share_params, name='gen-prelu-%d' % i)
"""
with tf.variable_scope("generator-%s" % name, reuse=reuse):
x = t.deconv2d(x,
f=self.channel,
k=6,
s=1,
reuse=False,
name='gen-' + name + '-deconv2d-3')
x = tf.nn.sigmoid(x, name='gen' + name + '-sigmoid-1')
"""
x = t.dense(x, self.n_input, reuse=False, name='gen-' + name + '-fc-%d' % loop)
x = tf.nn.sigmoid(x)
"""
return x
def generator(self, x, reuse=None):
with tf.variable_scope('generator', reuse=reuse):
def residual_block(x, f, name=""):
with tf.variable_scope(name, reuse=reuse):
skip_connection = tf.identity(x,
name='gen-skip_connection-1')
x = t.conv2d(x, f, 3, 1, name='gen-conv2d-1')
x = t.instance_norm(x, reuse=reuse, name='gen-inst_norm-1')
x = tf.nn.relu(x)
x = t.conv2d(x, f, 3, 1, name='gen-conv2d-2')
x = tf.nn.relu(x)
return skip_connection + x
shortcut = tf.identity(x, name='shortcut-init')
x = t.conv2d(x, self.gf_dim * 1, 7, 1, name='gen-conv2d-1')
x = t.instance_norm(x,
affine=False,
reuse=reuse,
name='gen-inst_norm-1')
x = tf.nn.relu(x)
for i in range(1, 3):
x = t.conv2d(x,
self.gf_dim * (2**i),
3,
2,
name='gen-conv2d-%d' % (i + 1))
x = t.instance_norm(x,
affine=False,
reuse=reuse,
name='gen-inst_norm-%d' % (i + 1))
x = tf.nn.relu(x)
# 9 Residual Blocks
for i in range(9):
x = residual_block(x,
self.gf_dim * 4,
name='gen-residual_block-%d' % (i + 1))
for i in range(1, 3):
x = t.deconv2d(x,
self.gf_dim * (2**i),
3,
2,
name='gen-deconv2d-%d' % i)
x = t.instance_norm(x,
affine=False,
reuse=reuse,
name='gen-inst_norm-%d' % (i + 3))
x = tf.nn.relu(x)
x = t.conv2d(x, self.gf_dim * 1, 7, 1, name='gen-conv2d-4')
x = tf.nn.tanh(x)
return shortcut + x
def u(x, f, name=''):
x = t.deconv2d(x,
f=f,
k=3,
s=2,
name='gen-u-deconv2d-%s' % name)
x = t.instance_norm(x, name='gen-u-ins_norm-%s' % name)
x = tf.nn.relu(x)
return x
def conv_in_relu(x, f, k, s, de=False, name=""):
if not de:
x = t.conv2d(x, f=f, k=k, s=s)
else:
x = t.deconv2d(x, f=f, k=k, s=s)
x = t.instance_norm(x, name=name)
x = tf.nn.relu(x)
return x
def decoder(self, x, reuse=None):
"""
(128)4c2s - (64)4c2s - (3)4c2s
:param x: embeddings
:param reuse: re-usable
:return: prob
"""
with tf.variable_scope('decoder', reuse=reuse):
x = t.deconv2d(x, self.df_dim * 2, 4, 2, name='dec-deconv2d-1')
x = t.batch_norm(x, name='dec-bn-1')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.df_dim * 1, 4, 2, name='dec-deconv2d-2')
x = t.batch_norm(x, name='dec-bn-2')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.channel, 4, 2, name='dec-deconv2d-3')
x = tf.nn.tanh(x)
return x
def generator(self, z, reuse=None, is_train=True):
with tf.variable_scope('generator', reuse=reuse):
x = t.dense(z, self.fc_unit, name='gen-fc-0')
x = t.batch_norm(x, is_train=is_train)
x = tf.nn.leaky_relu(x)
x = t.dense(x, self.gf_dim * 4 * 7 * 7, name='gen-fc-1')
x = t.batch_norm(x, is_train=is_train)
x = tf.nn.leaky_relu(x)
x = tf.reshape(x, [-1, 7, 7, self.gf_dim * 4])
x = t.deconv2d(x, self.gf_dim * 2, name='gen-deconv2d-0')
x = t.batch_norm(x, is_train=is_train)
x = tf.nn.leaky_relu(x)
logits = t.deconv2d(x, self.channel, name='gen-deconv2d-1')
prob = tf.nn.sigmoid(logits)
return prob
def decoder(self, z, reuse=None):
"""
:param z: embeddings
:param reuse: re-usable
:return: prob
"""
with tf.variable_scope('decoder', reuse=reuse):
x = z
for i in range(1, 4):
x = t.deconv2d(x,
self.df_dim * 8 // (2**i),
4,
2,
name='dec-deconv2d-%d' % i)
x = t.batch_norm(x, name='dec-bn-%d' % i)
x = tf.nn.leaky_relu(x)
x = t.deconv2d(x, self.channel, 4, 2, name='enc-deconv2d-4')
x = tf.nn.tanh(x)
return x
def generator(self, z, reuse=None, is_train=True):
with tf.variable_scope('generator', reuse=reuse):
x = t.dense(z, self.gf_dim * 8 * 4 * 4)
x = tf.reshape(x, [-1, 4, 4, self.gf_dim * 8])
x = t.batch_norm(x, is_train=is_train)
x = tf.nn.leaky_relu(x)
x = t.deconv2d(x, self.gf_dim * 4, name='g-deconv-1')
x = t.batch_norm(x, is_train=is_train)
x = tf.nn.leaky_relu(x)
x = t.deconv2d(x, self.gf_dim * 2, name='g-deconv-2')
x = t.batch_norm(x, is_train=is_train)
x = tf.nn.leaky_relu(x)
logits = t.deconv2d(x, self.channel, name='g-deconv-3')
prob = tf.nn.tanh(logits)
return prob
def generator(self, z, reuse=None, is_train=True):
""" Same as DCGAN Gen Net """
with tf.variable_scope('generator', reuse=reuse):
x = t.dense(z, self.gf_dim * 4 * 4 * 4, name='gen-fc-1')
x = tf.reshape(x, [-1, 4, 4, self.gf_dim * 4])
x = t.batch_norm(x, is_train=is_train, name='gen-bn-1')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.gf_dim * 2, 5, 2, name='gen-deconv2d-1')
x = t.batch_norm(x, is_train=is_train, name='gen-bn-2')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.gf_dim * 1, 5, 2, name='gen-deconv2d-2')
x = t.batch_norm(x, is_train=is_train, name='gen-bn-3')
x = tf.nn.relu(x)
x = t.deconv2d(x, self.channel, 5, 2, name='gen-deconv2d-3')
x = tf.nn.tanh(x)
return x
def generator(self, z, reuse=None, is_train=True):
with tf.variable_scope("generator", reuse=reuse):
x = t.dense(z, self.gf_dim * 7 * 7, name='gen-fc-1')
x = t.batch_norm(x, name='gen-bn-1')
x = tf.nn.leaky_relu(x, alpha=0.3)
x = tf.reshape(x, [-1, 7, 7, self.gf_dim])
for i in range(1, 3):
x = t.deconv2d(x,
self.gf_dim,
5,
2,
name='gen-deconv2d-%d' % (i + 1))
x = t.batch_norm(x,
is_train=is_train,
name='gen-bn-%d' % (i + 1))
x = tf.nn.leaky_relu(x, alpha=0.3)
x = t.deconv2d(x, 1, 5, 1, name='gen-deconv2d-3')
x = tf.nn.sigmoid(x)
return x
def generator(self, z, reuse=None):
"""
# referred architecture in the paper
: FC1024_BR-FC7x7x128_BR-(64)4dc2s_BR-(1)4dc2s_S
:param z: embeddings
:param reuse: re-usable
:return: prob
"""
with tf.variable_scope("generator", reuse=reuse):
x = t.dense(z, self.fc_unit * 4, name='g-fc-1')
x = tf.nn.leaky_relu(x)
x = t.dense(x, 7 * 7 * self.fc_unit // 2, name='g-fc-2')
x = tf.nn.leaky_relu(x)
x = tf.layers.flatten(x)
x = t.deconv2d(x, self.gf_dim, 4, 2, name='g-deconv2d-1')
x = tf.nn.leaky_relu(x)
x = t.deconv2d(x, 1, 4, 2, name='g-deconv2d-2')
x = tf.nn.sigmoid(x)
return x
def decoder(self, x, reuse=None):
"""
:param x: embeddings
:param reuse: re-usable
:return: prob
"""
with tf.variable_scope('decoder', reuse=reuse):
x = t.dense(x, self.gf_dim * 7 * 7, name='dec-fc-1')
x = tf.nn.leaky_relu(x)
x = tf.layers.flatten(x)
x = t.deconv2d(x, 1, 4, 2, name='dec-deconv2d-1')
x = tf.nn.sigmoid(x)
return x
def generator(self, z, scope_name, reuse=None, is_train=True):
with tf.variable_scope("%s" % scope_name, reuse=reuse):
x = t.dense(z, 4 * 4 * 8 * self.gf_dim)
x = tf.nn.leaky_relu(x)
x = tf.layers.flatten(x)
x = tf.reshape(x, (-1, 4, 4, 8))
for i in range(np.log2(self.height) - 2): # 0 ~ 3
x = t.deconv2d(x, self.gf_dim * (2 ** (i + 1)), k=4, s=2)
x = t.batch_norm(x, is_train=is_train)
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, 3)
return x
def generator(self, z, reuse=None, is_train=True):
with tf.variable_scope('generator', reuse=reuse):
x = t.dense(z, self.gf_dim * 8 * 4 * 4, name='gen-fc-1')
x = tf.reshape(x, [-1, 4, 4, self.gf_dim * 8])
x = t.batch_norm(x, is_train=is_train, name='gen-bn-1')
x = tf.nn.relu(x)
for i in range(1, 4):
x = t.deconv2d(x, self.gf_dim * 4, 3, 2, name='gen-deconv2d-%d' % i)
x = t.batch_norm(x, is_train=is_train, name='gen-bn-%d' % (i + 1))
x = tf.nn.relu(x)
x = t.conv2d(x, self.channel, 3, name='gen-conv2d-1')
x = tf.nn.sigmoid(x)
return x
def build_fcn(self):
vgg19_net = vgg19.VGG19(image=self.x)
net = vgg19_net.vgg19_net['pool5']
net = t.conv2d(net, 4096, k=7, s=1, name='conv6_1')
net = tf.nn.relu(net, name='relu6_1')
net = tf.nn.dropout(net, self.do_rate, name='dropout-6_1')
net = t.conv2d(net, 4096, k=1, s=1, name='conv7_1')
net = tf.nn.relu(net, name='relu7_1')
net = tf.nn.dropout(net, self.do_rate, name='dropout-7_1')
feature = t.conv2d(net, self.n_classes, k=1, s=1, name='conv8_1')
net = t.deconv2d(feature,
vgg19_net.vgg19_net['pool4'].get_shape()[3],
name='deconv_1')
net = tf.add(net, vgg19_net.vgg19_net['pool4'], name='fuse_1')
def generator(self, x, reuse=None):
"""
:param x: images
:param reuse: re-usable
:return: logits
"""
with tf.variable_scope("generator", reuse=reuse):
def conv_in_relu(x, f, k, s, de=False, name=""):
if not de:
x = t.conv2d(x, f=f, k=k, s=s)
else:
x = t.deconv2d(x, f=f, k=k, s=s)
x = t.instance_norm(x, name=name)
x = tf.nn.relu(x)
return x
x = conv_in_relu(x, f=self.gf_dim * 1, k=7, s=1, name="1")
# down-sampling
x = conv_in_relu(x, f=self.gf_dim * 2, k=4, s=2, name="2")
x = conv_in_relu(x, f=self.gf_dim * 4, k=4, s=2, name="3")
# bottleneck
for i in range(6):
x = residual_block(x, f=self.gf_dim * 4, name=str(i))
# up-sampling
x = conv_in_relu(x, self.gf_dim * 2, k=4, s=2, de=True, name="4")
x = conv_in_relu(x, self.gf_dim * 1, k=4, s=2, de=True, name="5")
x = t.deconv2d(x, f=3, k=7, s=1)
x = tf.nn.tanh(x)
return x
