def build_partial_resnet_block(inputres, mask_in, dim, name="resnet"):
"""build a single block of resnet.
:param inputres: inputres
:param dim: dim
:param name: name
:param padding: for tensorflow version use REFLECT; for pytorch version use
CONSTANT
:return: a single block of resnet.
"""
padding = "CONSTANT"
with tf.variable_scope(name):
inputres_ = tf.pad(inputres, [[0, 0], [1, 1], [1, 1], [0, 0]], padding)
mask_in_ = tf.pad(mask_in, [[0, 0], [1, 1], [1, 1], [0, 0]], padding)
out_res, mask = layers.general_partial_conv2d(inputres_,
mask_in_,
tf.constant(False,
dtype=bool),
dim,
3,
3,
1,
1,
0.02,
name="c1")
out_res = tf.pad(out_res, [[0, 0], [1, 1], [1, 1], [0, 0]], padding)
mask = tf.pad(mask, [[0, 0], [1, 1], [1, 1], [0, 0]], padding)
out_res_in = tf.multiply(out_res, mask)
out_res, mask = layers.general_partial_conv2d(out_res_in,
mask,
tf.constant(False,
dtype=bool),
dim,
3,
3,
1,
1,
0.02,
name="c2",
do_relu=False)
out_res_in = tf.multiply(out_res, mask)
mask_end = tf.cast(tf.greater(mask + mask_in, 0.), tf.float32)
return tf.nn.relu(out_res_in + inputres), mask_end
def discriminator_bis(inputdisc,
mask,
transition_rate,
donorm,
name="discriminator"):
""" Instead of normal convolutions, We make use of [Uhrig et al: Sparsity Invariant CNNs].
However we omit the normalizing factor they use by replacing it by 1. This removes the
effect of the bias coming from masked regions in the input.
"""
with tf.variable_scope(name):
mask = tf.cast(tf.greater_equal(mask, transition_rate), tf.float32)
inputdisc = tf.multiply(inputdisc, mask)
f = 4
padw = 2
pad_input = tf.pad(inputdisc,
[[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c1, mask_1 = layers.general_partial_conv2d(pad_input,
pad_mask,
donorm,
ndf,
f,
f,
2,
2,
0.02,
"VALID",
"c1",
relufactor=0.2)
o_c1 = tf.multiply(o_c1, mask_1)
pad_o_c1 = tf.pad(o_c1, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask_1, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c2, mask_2 = layers.general_partial_conv2d(pad_o_c1,
pad_mask,
donorm,
ndf * 2,
f,
f,
2,
2,
0.02,
"VALID",
"c2",
relufactor=0.2)
o_c2 = tf.multiply(o_c2, mask_2)
pad_o_c2 = tf.pad(o_c2, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask_2, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c3, mask_3 = layers.general_partial_conv2d(pad_o_c2,
pad_mask,
donorm,
ndf * 4,
f,
f,
2,
2,
0.02,
"VALID",
"c3",
relufactor=0.2)
o_c3 = tf.multiply(o_c3, mask_3)
pad_o_c3 = tf.pad(o_c3, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask_3, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c4, mask_4 = layers.general_partial_conv2d(pad_o_c3,
pad_mask,
donorm,
ndf * 8,
f,
f,
1,
1,
0.02,
"VALID",
"c4",
relufactor=0.2)
o_c4 = tf.multiply(o_c4, mask_4)
pad_o_c4 = tf.pad(o_c4, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask_4, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c5, mask_5 = layers.general_partial_conv2d(pad_o_c4,
pad_mask,
tf.constant(False,
dtype=bool),
1,
f,
f,
1,
1,
0.02,
"VALID",
"c5",
do_relu=False)
return o_c5
def build_generator_resnet_9blocks_bis(inputgen,
mask,
transition_rate,
name="generator",
skip=False):
""" Instead of normal convolutions, We make use of [Uhrig et al: Sparsity Invariant CNNs].
However we omit the normalizing factor they use by replaqcing it by 1. This removes the
effect of the bias coming from masked regions in the input.
"""
with tf.variable_scope(name):
f = 7
ks = 3
padding = "CONSTANT"
inputgen = tf.pad(inputgen, [[0, 0], [ks, ks], [ks, ks], [0, 0]],
padding)
mask = tf.pad(mask, [[0, 0], [ks, ks], [ks, ks], [0, 0]], padding)
o_c1, mask = layers.general_partial_conv2d(inputgen,
mask,
tf.constant(False,
dtype=bool),
ngf,
f,
f,
1,
1,
0.02,
name="c1")
o_c1_in = tf.multiply(o_c1, mask)
o_c2, mask = layers.general_partial_conv2d(o_c1_in,
mask,
tf.constant(False,
dtype=bool),
ngf * 2,
ks,
ks,
2,
2,
0.02,
padding='same',
name="c2")
o_c2_in = tf.multiply(o_c2, mask)
o_c3, mask = layers.general_partial_conv2d(o_c2_in,
mask,
tf.constant(False,
dtype=bool),
ngf * 4,
ks,
ks,
2,
2,
0.02,
padding='same',
name="c3")
o_c3_in = tf.multiply(o_c3, mask)
o_r1, mask_r1 = build_partial_resnet_block(o_c3_in, mask, ngf * 4,
"r1")
o_r2, mask_r2 = build_partial_resnet_block(o_r1, mask_r1, ngf * 4,
"r2")
o_r3, mask_r3 = build_partial_resnet_block(o_r2, mask_r2, ngf * 4,
"r3")
o_r4, mask_r4 = build_partial_resnet_block(o_r3, mask_r3, ngf * 4,
"r4")
o_r5, mask_r5 = build_partial_resnet_block(o_r4, mask_r4, ngf * 4,
"r5")
o_r6, mask_r6 = build_partial_resnet_block(o_r5, mask_r5, ngf * 4,
"r6")
o_r7, mask_r7 = build_partial_resnet_block(o_r6, mask_r6, ngf * 4,
"r7")
o_r8, mask_r8 = build_partial_resnet_block(o_r7, mask_r7, ngf * 4,
"r8")
o_r9, mask_r9 = build_partial_resnet_block(o_r8, mask_r8, ngf * 4,
"r9")
o_c4 = layers.general_deconv2d(o_r9, [BATCH_SIZE, 128, 128, ngf * 2],
ngf * 2, ks, ks, 2, 2, 0.02, "SAME",
"c4")
o_c5 = layers.general_deconv2d(o_c4, [BATCH_SIZE, 256, 256, ngf], ngf,
ks, ks, 2, 2, 0.02, "SAME", "c5")
o_c6 = layers.general_conv2d(o_c5,
IMG_CHANNELS,
f,
f,
1,
1,
0.02,
"SAME",
"c6",
do_norm=False,
do_relu=False)
if skip is True:
out_gen = tf.nn.tanh(inputgen + o_c6, "t1")
else:
out_gen = tf.nn.tanh(o_c6, "t1")
return out_gen
def discriminator_bis(inputdisc,
mask,
transition_rate,
donorm,
name="discriminator"):
with tf.variable_scope(name):
mask = tf.cast(tf.greater_equal(mask, transition_rate), tf.float32)
inputdisc = tf.multiply(inputdisc, mask)
f = 4
padw = 2
pad_input = tf.pad(inputdisc,
[[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c1, mask_1 = layers.general_partial_conv2d(pad_input,
pad_mask,
donorm,
ndf,
f,
f,
2,
2,
0.02,
"VALID",
"c1",
relufactor=0.2)
# o_c1 = tf.multiply(o_c1, mask_1)
pad_o_c1 = tf.pad(o_c1, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask_1, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c2, mask_2 = layers.general_partial_conv2d(pad_o_c1,
pad_mask,
donorm,
ndf * 2,
f,
f,
2,
2,
0.02,
"VALID",
"c2",
relufactor=0.2)
# o_c2 = tf.multiply(o_c2, mask_2)
pad_o_c2 = tf.pad(o_c2, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask_2, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c3, mask_3 = layers.general_partial_conv2d(pad_o_c2,
pad_mask,
donorm,
ndf * 4,
f,
f,
2,
2,
0.02,
"VALID",
"c3",
relufactor=0.2)
# o_c3 = tf.multiply(o_c3, mask_3)
pad_o_c3 = tf.pad(o_c3, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask_3, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c4, mask_4 = layers.general_partial_conv2d(pad_o_c3,
pad_mask,
donorm,
ndf * 8,
f,
f,
1,
1,
0.02,
"VALID",
"c4",
relufactor=0.2)
# o_c4 = tf.multiply(o_c4, mask_4)
pad_o_c4 = tf.pad(o_c4, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
pad_mask = tf.pad(mask_4, [[0, 0], [padw, padw], [padw, padw], [0, 0]],
"CONSTANT")
o_c5, mask_5 = layers.general_partial_conv2d(pad_o_c4,
pad_mask,
tf.constant(False,
dtype=bool),
1,
f,
f,
1,
1,
0.02,
"VALID",
"c5",
do_relu=False)
return o_c5
def build_generator_resnet_9blocks_bis(inputgen,
mask,
transition_rate,
name="generator",
skip=False):
with tf.variable_scope(name):
f = 7
ks = 3
padding = "CONSTANT"
inputgen = tf.pad(inputgen, [[0, 0], [ks, ks], [ks, ks], [0, 0]],
padding)
mask = tf.pad(mask, [[0, 0], [ks, ks], [ks, ks], [0, 0]], padding)
o_c1, mask = layers.general_partial_conv2d(inputgen,
mask,
tf.constant(False,
dtype=bool),
ngf,
f,
f,
1,
1,
0.02,
name="c1")
# o_c1_in = tf.multiply(o_c1, mask)
o_c2, mask = layers.general_partial_conv2d(o_c1,
mask,
tf.constant(False,
dtype=bool),
ngf * 2,
ks,
ks,
2,
2,
0.02,
padding='same',
name="c2")
# o_c2_in = tf.multiply(o_c2, mask)
o_c3, mask = layers.general_partial_conv2d(o_c2,
mask,
tf.constant(False,
dtype=bool),
ngf * 4,
ks,
ks,
2,
2,
0.02,
padding='same',
name="c3")
# o_c3_in = tf.multiply(o_c3, mask)
#o_r1, mask_r1 = build_partial_resnet_block(o_c3, mask, ngf * 4, "r1")
#o_r2, mask_r2 = build_partial_resnet_block(o_r1, mask_r1, ngf * 4, "r2")
#o_r3, mask_r3 = build_partial_resnet_block(o_r2, mask_r2, ngf * 4, "r3")
#o_r4, mask_r4 = build_partial_resnet_block(o_r3, mask_r3, ngf * 4, "r4")
#o_r5, mask_r5 = build_partial_resnet_block(o_r4, mask_r4, ngf * 4, "r5")
#o_r6, mask_r6 = build_partial_resnet_block(o_r5, mask_r5, ngf * 4, "r6")
#o_r7, mask_r7 = build_partial_resnet_block(o_r6, mask_r6, ngf * 4, "r7")
#o_r8, mask_r8 = build_partial_resnet_block(o_r7, mask_r7, ngf * 4, "r8")
#o_r9, mask_r9 = build_partial_resnet_block(o_r8, mask_r8, ngf * 4, "r9")
o_r1 = build_resnet_block(o_c3, ngf * 4, "r1", padding)
o_r2 = build_resnet_block(o_r1, ngf * 4, "r2", padding)
o_r3 = build_resnet_block(o_r2, ngf * 4, "r3", padding)
o_r4 = build_resnet_block(o_r3, ngf * 4, "r4", padding)
o_r5 = build_resnet_block(o_r4, ngf * 4, "r5", padding)
o_r6 = build_resnet_block(o_r5, ngf * 4, "r6", padding)
o_r7 = build_resnet_block(o_r6, ngf * 4, "r7", padding)
o_r8 = build_resnet_block(o_r7, ngf * 4, "r8", padding)
o_r9 = build_resnet_block(o_r8, ngf * 4, "r9", padding)
o_c4 = layers.general_deconv2d(o_r9, [BATCH_SIZE, 128, 128, ngf * 2],
ngf * 2, ks, ks, 2, 2, 0.02, "SAME",
"c4")
o_c5 = layers.general_deconv2d(o_c4, [BATCH_SIZE, 256, 256, ngf], ngf,
ks, ks, 2, 2, 0.02, "SAME", "c5")
o_c6 = layers.general_conv2d(o_c5,
IMG_CHANNELS,
f,
f,
1,
1,
0.02,
"SAME",
"c6",
do_norm=False,
do_relu=False)
if skip is True:
out_gen = tf.nn.tanh(inputgen + o_c6, "t1")
else:
out_gen = tf.nn.tanh(o_c6, "t1")
return out_gen