def discriminator(self, x, reuse=None, name=""):
"""
:param x: 128x128x3 images
:param reuse: re-usability
:param name: name
:return: logits, prob
"""
with tf.variable_scope('discriminator-%s' % name, reuse=reuse):
def residual_block(x, f, name=''):
x = t.conv2d(x, f=f, k=4, s=2, name='disc-conv2d-%s' % name)
x = t.instance_norm(x, name='disc-ins_norm-%s' % name)
x = tf.nn.leaky_relu(x, alpha=0.2)
return x
x = t.conv2d(x, f=self.df_dim, name='disc-conv2d-0')
x = tf.nn.leaky_relu(x, alpha=0.2)
x = residual_block(x, f=self.df_dim * 2, name='1')
x = residual_block(x, f=self.df_dim * 4, name='2')
x = residual_block(x, f=self.df_dim * 8, name='3')
# for 256x256x3 images
# x = residual_block(x, f=self.df_dim * 8, name='4')
# x = residual_block(x, f=self.df_dim * 8, name='5')
logits = t.conv2d(x, f=1, name='disc-con2d-last')
# prob = tf.nn.sigmoid(logits)
return logits
def discriminator(self, x, reuse=None):
"""
# Following a D Network, CiFar-like-hood, referred in the paper
:param x: images
:param y: labels
:param reuse: re-usable
:return: classification, probability (fake or real), network
"""
with tf.variable_scope("discriminator", reuse=reuse):
x = t.conv2d(x, self.df_dim, 3, 2, name='disc-conv2d-1')
x = tf.nn.leaky_relu(x, alpha=0.2)
x = tf.layers.dropout(x, 0.5, name='disc-dropout2d-1')
for i in range(5):
x = t.conv2d(x, self.df_dim * (2 ** (i + 1)), k=3, s=(i % 2 + 1), name='disc-conv2d-%d' % (i + 2))
x = t.batch_norm(x, reuse=reuse, name="disc-bn-%d" % (i + 1))
x = tf.nn.leaky_relu(x, alpha=0.2)
x = tf.layers.dropout(x, 0.5, name='disc-dropout2d-%d' % (i + 1))
net = tf.layers.flatten(x)
cat = t.dense(net, self.n_classes, name='disc-fc-cat')
disc = t.dense(net, 1, name='disc-fc-disc')
return cat, disc, net
def discriminator(self, x, reuse=None):
"""
# Following a network architecture referred in the paper
:param x: Input images (-1, 384, 384, 3)
:param reuse: re-usability
:return: HR (High Resolution) or SR (Super Resolution) images
"""
with tf.variable_scope("discriminator", reuse=reuse):
x = t.conv2d(x, self.df_dim, 3, 1, name='n64s1-1')
x = tf.nn.leaky_relu(x)
strides = [2, 1]
filters = [1, 2, 2, 4, 4, 8, 8]
for i, f in enumerate(filters):
x = t.conv2d(x,
f=f,
k=3,
s=strides[i % 2],
name='n%ds%d-%d' % (f, strides[i % 2], i + 1))
x = t.batch_norm(x, name='n%d-bn-%d' % (f, i + 1))
x = tf.nn.leaky_relu(x)
x = tf.layers.flatten(x) # (-1, 96 * 96 * 64)
x = t.dense(x, 1024, name='disc-fc-1')
x = tf.nn.leaky_relu(x)
x = t.dense(x, 1, name='disc-fc-2')
# x = tf.nn.sigmoid(x)
return x
def encoder(self, x, reuse=None):
"""
:param x: Input images (32x32x3 or 64x64x3)
:param reuse: re-usable
:return: embeddings
"""
with tf.variable_scope('encoder', reuse=reuse):
repeat = int(np.log2(self.height)) - 2
x = t.conv2d(x, f=self.df_dim, name="enc-conv2d-1")
x = tf.nn.elu(x)
for i in range(1, repeat + 1):
f = self.df_dim * i
x = t.conv2d(x, f, 3, 1, name="enc-conv2d-%d" % (i * 2))
x = tf.nn.elu(x)
x = t.conv2d(x, f, 3, 1, name="enc-conv2d-%d" % (i * 2 + 1))
x = tf.nn.elu(x)
if i < repeat:
"""
You can choose one of them. max-pool or avg-pool or conv-pool.
Speed Order : conv-pool > avg-pool > max-pool. i guess :)
"""
x = t.conv2d(x, f, 3, 2,
name='enc-conv2d-pool-%d' % i) # conv pooling
x = tf.nn.elu(x)
x = t.flatten(x)
x = t.dense(x, self.z_dim, name='enc-fc-1') # normally, (-1, 128)
return x
def discriminator(self, x, y=None, reuse=None, is_train=True):
"""
:param x: images
:param y: labels
:param reuse: re-usable
:param is_train: en/disable batch_norm, default True
:return: fm, logits
"""
with tf.variable_scope("discriminator", reuse=reuse):
if y:
raise NotImplementedError("[-] Not Implemented Yet...")
x = t.conv2d(x, f=self.gf_dim * 1, name="disc-conv2d-1")
x = tf.nn.leaky_relu(x)
for i in range(1, 4):
x = t.conv2d(x,
f=self.gf_dim * (2**i),
name="disc-conv2d-%d" % (i + 1))
x = t.batch_norm(x,
is_train=is_train,
name='disc-bn-%d' % (i + 1))
x = tf.nn.leaky_relu(x)
feature_match = x # (-1, 8, 8, 512)
x = t.flatten(x)
x = t.dense(x, 1, name='disc-fc-1')
return feature_match, 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 generator(self, x, reuse=None, is_train=True):
"""
:param x: LR (Low Resolution) images, (-1, 96, 96, 3)
:param reuse: scope re-usability
:param is_train: is trainable, default True
:return: SR (Super Resolution) images, (-1, 384, 384, 3)
"""
with tf.variable_scope("generator", reuse=reuse):
def residual_block(x, f, name="", _is_train=True):
with tf.variable_scope(name):
shortcut = tf.identity(x, name='n64s1-shortcut')
x = t.conv2d(x, f, 3, 1, name="n64s1-1")
x = t.batch_norm(x, is_train=_is_train, name="n64s1-bn-1")
x = t.prelu(x, reuse=reuse, name='n64s1-prelu-1')
x = t.conv2d(x, f, 3, 1, name="n64s1-2")
x = t.batch_norm(x, is_train=_is_train, name="n64s1-bn-2")
x = tf.add(x, shortcut)
return x
x = t.conv2d(x, self.gf_dim, 9, 1, name='n64s1-1')
x = t.prelu(x, name='n64s1-prelu-1')
skip_conn = tf.identity(x, name='skip_connection')
# B residual blocks
for i in range(1, 17): # (1, 9)
x = residual_block(x,
self.gf_dim,
name='b-residual_block_%d' % i,
_is_train=is_train)
x = t.conv2d(x, self.gf_dim, 3, 1, name='n64s1-3')
x = t.batch_norm(x, is_train=is_train, name='n64s1-bn-3')
x = tf.add(x, skip_conn)
# sub-pixel conv2d blocks
for i in range(1, 3):
x = t.conv2d(x,
self.gf_dim * 4,
3,
1,
name='n256s1-%d' % (i + 2))
x = t.sub_pixel_conv2d(x, f=None, s=2)
x = t.prelu(x, name='n256s1-prelu-%d' % i)
x = t.conv2d(x, self.channel, 9, 1,
name='n3s1') # (-1, 384, 384, 3)
x = tf.nn.tanh(x)
return x
def residual_block(x, f, name="0"):
with tf.variable_scope("residual_block-" + name):
scope_name = "residual_block-" + name
x = t.conv2d(x, f=f, k=3, s=1)
x = t.instance_norm(x, affine=True, name=scope_name + '_0')
x = tf.nn.relu(x)
x = t.conv2d(x, f=f, k=3, s=1)
x = t.instance_norm(x, affine=True, name=scope_name + '_1')
return x
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
def residual_block(x, f, name="", _is_train=True):
with tf.variable_scope(name):
shortcut = tf.identity(x, name='n64s1-shortcut')
x = t.conv2d(x, f, 3, 1, name="n64s1-1")
x = t.batch_norm(x, is_train=_is_train, name="n64s1-bn-1")
x = t.prelu(x, reuse=reuse, name='n64s1-prelu-1')
x = t.conv2d(x, f, 3, 1, name="n64s1-2")
x = t.batch_norm(x, is_train=_is_train, name="n64s1-bn-2")
x = tf.add(x, shortcut)
return x
def generator(self, x, reuse=None, name=""):
""" The form of Auto-Encoder
:param x: 128x128x3 images
:param reuse: re-usability
:param name: name
:return: logits, prob
"""
with tf.variable_scope('generator-%s' % name, reuse=reuse):
def d(x, f, name=''):
x = t.conv2d(x, f=f, k=3, s=2, name='gen-d-conv2d-%s' % name)
x = t.instance_norm(x, name='gen-d-ins_norm-%s' % name)
x = tf.nn.relu(x)
return x
def R(x, f, name=''):
x = t.conv2d(x, f=f, k=3, s=1, name='gen-R-conv2d-%s-0' % name)
x = t.conv2d(x, f=f, k=3, s=1, name='gen-R-conv2d-%s-1' % name)
x = t.instance_norm(x, name='gen-R-ins_norm-%s' % name)
x = tf.nn.relu(x)
return 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
x = t.conv2d(x, f=self.gf_dim, k=7, s=1, name='gen-conv2d-0')
x = d(x, self.gf_dim * 2, name='1')
x = d(x, self.gf_dim * 4, name='2')
for i in range(1, 7):
x = R(x, self.gf_dim * 4, name=str(i))
x = u(x, self.gf_dim * 4, name='1')
x = u(x, self.gf_dim * 2, name='2')
logits = t.conv2d(x, f=3, k=7, s=1, name='gen-conv2d-1')
prob = tf.nn.tanh(logits)
return prob
def discriminator(self, x, reuse=None):
with tf.variable_scope('discriminator', reuse=reuse):
x = tf.reshape(x, (-1, self.height, self.width, self.channel))
x = t.conv2d(x, self.df_dim, 5, 2, name='disc-conv2d-1')
x = tf.nn.leaky_relu(x)
for i in range(1, 3):
x = t.conv2d(x, self.df_dim, 5, 2, name='disc-conv2d-%d' % (i + 1))
x = t.batch_norm(x, reuse=reuse, name='disc-bn-%d' % i)
x = tf.nn.leaky_relu(x)
x = t.flatten(x)
x = t.dense(x, 1, name='disc-fc-1')
return x
def generator(self, x, y, z, scale=32, reuse=None, do_rate=0.5):
"""
:param x: images to fake
:param y: classes
:param z: noise
:param scale: image size
:param reuse: variable re-use
:param do_rate: dropout rate
:return: logits
"""
assert scale % 8 == 0 # 32, 16, 8
with tf.variable_scope('generator_{0}'.format(scale), reuse=reuse):
if scale == 8:
h = tf.concat([z, y], axis=1)
h = t.dense(h, self.g_fc_unit, name='gen-fc-1')
h = tf.nn.relu(h)
h = tf.layers.dropout(h, do_rate, name='gen-dropout-1')
h = t.dense(h, self.g_fc_unit, name='gen-fc-2')
h = tf.nn.relu(h)
h = tf.layers.dropout(h, do_rate, name='gen-dropout-2')
h = t.dense(h, self.channel * 8 * 8, name='gen-fc-3')
h = tf.reshape(h, [-1, 8, 8, self.channel])
else:
y = t.dense(y, scale * scale, name='gen-fc-y')
y = tf.reshape(y, [-1, scale, scale, 1])
z = tf.reshape(z, [-1, scale, scale, 1])
h = tf.concat([z, y, x], axis=3) # concat into 5 dims
h = t.conv2d(h, self.gf_dim * 1, 5, 1, name='gen-deconv2d-1')
h = tf.nn.relu(h)
h = t.conv2d(h, self.gf_dim * 1, 5, 1, name='gen-deconv2d-2')
h = tf.nn.relu(h)
h = t.conv2d(h, self.channel, 5, 1, name='gen-conv2d-3')
h = tf.nn.tanh(h)
return h
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 encoder(self, x, reuse=None):
"""
(64)4c2s - (128)4c2s - (256)4c2s
:param x: images
:param reuse: re-usable
:return: logits
"""
with tf.variable_scope('encoder', reuse=reuse):
x = t.conv2d(x, self.df_dim * 1, 4, 2, name='enc-conv2d-1')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 2, 4, 2, name='enc-conv2d-2')
x = t.batch_norm(x, name='enc-bn-1')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 4, 4, 2, name='enc-conv2d-3')
x = t.batch_norm(x, name='enc-bn-2')
x = tf.nn.leaky_relu(x)
return x
def discriminator(self, x, reuse=None):
"""
:param x: images
:param reuse: re-usable
:return: logits
"""
with tf.variable_scope("discriminator", reuse=reuse):
x = t.conv2d(x, self.df_dim * 1, name='d-conv2d-1')
x = tf.nn.leaky_relu(x)
for i in range(1, 3):
x = t.conv2d(x,
self.df_dim * (2**i),
name='d-conv2d-%d' % (i + 1))
x = t.batch_norm(x)
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, 1, s=1, name='d-conv2d-4')
return x
def discriminator(self, x, scope_name, reuse=None):
with tf.variable_scope("%s" % scope_name, reuse=reuse):
x = t.conv2d(x, f=self.df_dim, k=4, s=1) # 64 x 64 x 3
x = tf.nn.leaky_relu(x)
for i in range(np.log2(x.get_shape()[1]) - 2): # 0 ~ 3
x = t.conv2d(x, self.df_dim * (2**(i + 1)), k=4, s=2)
x = t.batch_norm(x)
x = tf.nn.leaky_relu(x)
# (-1, 4, 4, 512)
x = tf.layers.flatten(x)
x = t.dense(x, 512)
x = tf.nn.leaky_relu(x)
x = t.dense(x, 1)
x = tf.sigmoid(x)
return x
def discriminator(self, x, reuse=None):
""" Same as DCGAN Disc Net """
with tf.variable_scope('discriminator', reuse=reuse):
x = t.conv2d(x, self.df_dim * 1, 5, 2, name='disc-conv2d-1')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 2, 5, 2, name='disc-conv2d-2')
x = t.batch_norm(x, name='disc-bn-1')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 4, 5, 2, name='disc-conv2d-3')
x = t.batch_norm(x, name='disc-bn-2')
x = tf.nn.leaky_relu(x)
x = tf.layers.flatten(x)
logits = t.dense(x, 1, name='disc-fc-1')
prob = tf.nn.sigmoid(logits)
return prob, logits
def non_local_block(x, f, sub_sampling=False, name="nonlocal"):
""" non-local block, https://arxiv.org/pdf/1711.07971.pdf """
with tf.variable_scope("non_local_block-%s" % name):
with tf.name_scope("theta"):
theta = t.conv2d(x, f=f, k=1, s=1, name="theta")
if sub_sampling:
theta = tf.layers.max_pooling2d(theta,
pool_size=(2, 2),
name="max_pool-theta")
theta = tf.reshape(theta,
(-1, theta.get_shape().as_list()[-1]))
with tf.name_scope("phi"):
phi = t.conv2d(x, f=f, k=1, s=1, name="phi")
if sub_sampling:
phi = tf.layers.max_pooling2d(theta,
pool_size=(2, 2),
name="max_pool-phi")
phi = tf.reshape(phi, (-1, phi.get_shape().as_list()[-1]))
phi = tf.transpose(phi, [1, 0])
with tf.name_scope("g"):
g = t.conv2d(x, f=f, k=1, s=1, name="g")
if sub_sampling:
g = tf.layers.max_pooling2d(theta,
pool_size=(2, 2),
name="max_pool-g")
g = tf.reshape(g, (-1, g.get_shape().as_list()[-1]))
with tf.name_scope("self-attention"):
theta_phi = tf.tensordot(theta, phi, axis=-1)
theta_phi = tf.nn.softmax(theta_phi)
theta_phi_g = tf.tensordot(theta_phi, g, axis=-1)
theta_phi_g = t.conv2d(theta_phi_g,
f=f,
k=1,
s=1,
name="theta_phi_g")
return x + theta_phi_g
def encoder(self, x, reuse=None):
with tf.variable_scope('encoder', reuse=reuse):
x = t.conv2d(x, self.df_dim * 1, 5, 2, name='enc-conv2d-1')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 2, 5, 2, name='enc-conv2d-2')
x = t.batch_norm(x, name='enc-bn-1')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 4, 5, 2, name='enc-conv2d-3')
x = t.batch_norm(x, name='enc-bn-2')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 8, 5, 2, name='enc-conv2d-4')
x = t.batch_norm(x, name='enc-bn-3')
x = tf.nn.leaky_relu(x)
x = tf.layers.flatten(x)
x = t.dense(x, self.z_dim, name='enc-fc-1')
return x
def discriminator(self, x, reuse=None):
with tf.variable_scope('discriminator', reuse=reuse):
x = t.conv2d(x, self.df_dim * 1, 5, 2, name='disc-conv2d-1')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 2, 5, 2, name='disc-conv2d-2')
x = t.batch_norm(x, name='disc-bn-1')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 4, 5, 2, name='disc-conv2d-3')
x = t.batch_norm(x, name='disc-bn-2')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 8, 5, 2, name='disc-conv2d-4')
x = t.batch_norm(x, name='disc-bn-3')
x = tf.nn.leaky_relu(x)
x = tf.layers.flatten(x)
x = t.dense(x, 1, name='disc-fc-1')
x = tf.nn.sigmoid(x)
return x
def discriminator(self, x, reuse=None):
"""
:param x: images
:param reuse: re-usable
:return: logits
"""
with tf.variable_scope("discriminator", reuse=reuse):
x = t.conv2d(x, self.df_dim * 1, 4, 2, name='disc-conv2d-1')
x = tf.nn.leaky_relu(x, alpha=0.1)
x = t.conv2d(x, self.df_dim * 2, 4, 2, name='disc-conv2d-2')
x = t.batch_norm(x, name='disc-bn-1')
x = tf.nn.leaky_relu(x, alpha=0.1)
x = t.conv2d(x, self.df_dim * 4, 4, 2, name='disc-conv2d-3')
x = t.batch_norm(x, name='disc-bn-2')
x = tf.nn.leaky_relu(x, alpha=0.1)
x = t.conv2d(x, self.df_dim * 8, 4, 2, name='disc-conv2d-4')
x = t.batch_norm(x, name='disc-bn-3')
x = tf.nn.leaky_relu(x, alpha=0.1)
x = tf.layers.flatten(x)
x = t.dense(x, self.fc_unit, name='disc-fc-1')
x = t.batch_norm(x, name='disc-bn-4')
x = tf.nn.leaky_relu(x, alpha=0.1)
x = t.dense(x, 1 + self.n_cont + self.n_cat, name='disc-fc-2')
prob, cont, cat = x[:,
0], x[:, 1:1 +
self.n_cont], x[:, 1 +
self.n_cont:] # logits
prob = tf.nn.sigmoid(prob) # probability
cat = tf.nn.softmax(cat) # categories
return prob, cont, cat
def decoder(self, z, reuse=None):
"""
:param z: embeddings
:param reuse: re-usable
:return: logits
"""
with tf.variable_scope('decoder', reuse=reuse):
repeat = int(np.log2(self.height)) - 2
x = t.dense(z, self.z_dim * 8 * 8, name='dec-fc-1')
x = tf.reshape(x, [-1, 8, 8, self.z_dim])
# shortcut = tf.identity(x, name='shortcut')
for i in range(1, repeat + 1):
x = t.conv2d(x,
self.gf_dim,
3,
1,
name="dec-conv2d-%d" % (i * 2 - 1))
x = tf.nn.elu(x)
x = t.conv2d(x,
self.gf_dim,
3,
1,
name="dec-conv2d-%d" % (i * 2))
x = tf.nn.elu(x)
# if i < 3:
# x = tf.add(x, shortcut)
if i < repeat:
x = t.up_sampling(x, tf.image.ResizeMethod.NEAREST_NEIGHBOR
) # NN up-sampling
x = t.conv2d(x, f=self.channel)
x = tf.nn.tanh(x)
return x
def discriminator(self, x, reuse=None):
with tf.variable_scope('discriminator', reuse=reuse):
x = t.conv2d(x, self.df_dim * 1, 4, 2, name='disc-conv2d-1')
x = tf.nn.leaky_relu(x)
for i in range(1, 3):
x = t.conv2d(x,
self.df_dim * (2**i),
4,
2,
name='disc-conv2d-%d' % (i + 1))
x = t.instance_norm(x,
reuse=reuse,
name='disc-inst_norm-%d' % i)
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, self.df_dim * 8, 4, 1, name='disc-conv2d-4')
x = t.instance_norm(x, reuse=reuse, name='disc-inst_norm-3')
x = tf.nn.leaky_relu(x)
x = t.conv2d(x, 1, 4, 1, name='disc-conv2d-5')
return x
def discriminator(self, x, y=None, share_params=False, reuse=False, name=""):
with tf.variable_scope("discriminator-%s" % name, reuse=reuse):
x = tf.reshape(x, (-1, self.height, self.width, self.channel))
x = t.conv2d(x, f=self.df_dim * 1, k=5, s=2, reuse=False, name='disc-' + name + '-conv2d-1')
x = t.prelu(x, reuse=False, name='disc-' + name + '-prelu-1')
# x = tf.layers.max_pooling2d(x, pool_size=2, strides=2, padding='SAME',
# name='disc-' + name + '-max_pool2d-1')
x = t.conv2d(x, f=self.df_dim * 2, k=5, s=2, reuse=False, name='disc-' + name + '-conv2d-2')
x = t.batch_norm(x, reuse=False, name='disc-' + name + '-bn-1')
x = t.prelu(x, reuse=False, name='disc-' + name + '-prelu-2')
# x = tf.layers.max_pooling2d(x, pool_size=2, strides=2, padding='SAME',
# name='disc-' + name + '-max_pool2d-2')
x = tf.layers.flatten(x)
x = t.dense(x, self.fc_d_unit, reuse=share_params, name='disc-fc-1')
x = t.batch_norm(x, reuse=share_params, name='disc-bn-2')
x = t.prelu(x, reuse=share_params, name='disc-prelu-3')
x = t.dense(x, 1, reuse=share_params, name='disc-fc-2')
return x
def encoder(self, x, reuse=None):
"""
:param x: images
:param reuse: re-usable
:return: logits
"""
with tf.variable_scope('encoder', reuse=reuse):
for i in range(1, 5):
x = t.conv2d(x, self.df_dim * (2 ** (i - 1)), 4, 2, name='enc-conv2d-%d' % i)
if i > 1:
x = t.batch_norm(x, name='enc-bn-%d' % (i - 1))
x = tf.nn.leaky_relu(x)
return x
def discriminator(self, x, reuse=None):
with tf.variable_scope('discriminator', reuse=reuse):
for i in range(1, 4):
x = t.conv2d(x,
self.gf_dim * (2**(i - 1)),
3,
2,
name='disc-conv2d-%d' % i)
x = t.batch_norm(x, name='disc-bn-%d' % i)
x = tf.nn.leaky_relu(x, alpha=0.3)
x = tf.layers.flatten(x)
x = t.dense(x, 1, name='disc-fc-1')
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 discriminator(self, x, reuse=None):
with tf.variable_scope("discriminator", reuse=reuse):
for i in range(1, 3):
x = t.conv2d(x,
self.df_dim * i,
5,
2,
name='disc-conv2d-%d' % i)
x = t.batch_norm(x, name='disc-bn-%d' % i)
x = tf.nn.leaky_relu(x, alpha=0.3)
x = t.flatten(x)
logits = t.dense(x, 1, name='disc-fc-1')
prob = tf.nn.sigmoid(logits)
return prob, logits
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
