def block(self, name, x, chout, spout, is_train, is_last=False):
with tf.variable_scope(name, reuse=self._reuse):
if not is_last:
G = ops.deconv2d(x, [self._batch_size, spout, spout, chout],
4,
4,
2,
2,
name='conv',
use_sn=self._sn,
xavier=True)
G = ops.norms(G, is_train, 'norm', self._norm)
G = ops.acts(G, self._activation)
else:
G = ops.deconv2d(x, [self._batch_size, spout, spout, chout],
3,
3,
1,
1,
name='conv',
use_sn=self._sn,
xavier=True)
G = ops.acts(G, 'tanh')
return G
def block(self, name, x, chout, is_train, is_last=False, is_first=False):
with tf.variable_scope(name, reuse=self._reuse):
D = ops.conv2d(x,
chout,
3,
3,
1,
1,
0.02,
'conv1',
use_sn=self._sn,
xavier=True)
if not is_first:
D = ops.norms(D, is_train, 'norm1', self._norm)
D = ops.acts(D, self._activation)
if not is_last:
D = ops.conv2d(D,
chout * 2,
4,
4,
2,
2,
0.02,
'conv2',
use_sn=self._sn,
xavier=True)
if not is_first:
D = ops.norms(D, is_train, 'norm2', self._norm)
D = ops.acts(D, self._activation)
return D
def FCblock(self, name, x, chout, is_train, is_last=False):
with tf.variable_scope(name, reuse=self._reuse):
C = ops.linear(x, chout, 'linear')
if not is_last:
C = ops.norms(C, is_train, 'norm', self._norm)
C = ops.acts(C, self._activation)
return C
def __call__(self, z, y=None, is_train=True):
with tf.variable_scope(self.name, reuse=self._reuse):
if y is not None:
z = tf.concat([z, y], 1)
y = tf.reshape(y, [self._batch_size, 1, 1, y.shape[-1].value])
# 16*16*512
G = ops.linear(z,
16 * 16 * self._nf * 8,
'linear1',
use_sn=self._sn)
# 16*16*512
G = tf.reshape(G, [-1, 16, 16, self._nf * 8])
G = ops.norms(G, is_train, 'norm1', self._norm)
G = ops.acts(G, self._activation)
# 32 32 256
if y is not None:
G = ops.conv_cond_concat(G, y)
G = self.block('block1', G, self._nf * 4, 32, is_train)
# 64 64 128
if y is not None:
G = ops.conv_cond_concat(G, y)
G = self.block('block2', G, self._nf * 2, 64, is_train)
# 128 128 64
if y is not None:
G = ops.conv_cond_concat(G, y)
G = self.block('block3', G, self._nf, 128, is_train)
# 128 128 3
G = self.block('block4', G, 3, 128, is_train, True)
self._reuse = True
self.var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
self.name)
return G
def convblock(self, name, x, chout, is_train, is_last=False, s=2):
with tf.variable_scope(name, reuse=self._reuse):
Cn = ops.conv2d(x, chout, 4, 4, s, s, xavier=True)
if not is_last:
Cn = ops.norms(Cn, is_train, 'norm', self._norm)
Cn = ops.acts(Cn, self._activation)
return Cn
def block(self, name, x, chout, is_train, is_norm=True, is_act=True):
with tf.variable_scope(name, reuse=self._reuse):
M = ops.linear(x, chout, 'linear')
if is_norm:
M = ops.norms(M, is_train, 'norm', self._norm)
if is_act:
M = ops.acts(M, self._activation)
return M
def block(self, name, x, chout, is_train, use_norm=True):
with tf.variable_scope(name, reuse=self._reuse):
C = ops.conv2d(x,
chout,
5,
5,
2,
2,
0.02,
'conv',
use_sn=self._sn,
xavier=True)
if use_norm:
C = ops.norms(C, is_train, 'norm', self._norm)
C = ops.acts(C, self._activation)
return C
def __call__(self, z, y=None, is_train=True):
with tf.variable_scope(self.name, reuse=self._reuse):
if y is not None:
z = tf.concat([z, y], 1)
# 4*4*512
G = ops.linear(z, 4 * 4 * self._nf * 4, 'linear')
# 4 4 512
G = tf.reshape(G, [-1, 4, 4, self._nf * 4])
G = ops.norms(G, is_train, 'norm', self._norm)
G = ops.acts(G, self._activation)
# 7 7 256
G = self.block('block1', G, self._nf * 2, 7, is_train)
# 14 14 128
G = self.block('block2', G, self._nf, 14, is_train)
# 28 28 1
G = self.block('block3', G, 1, 28, is_train, True)
self._reuse = True
self.var_list = tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES,
self.name)
return G