def build_generator_resnet_9blocks(inputgen, inputimg, name="generator", skip=False):
with tf.variable_scope(name):
f = 7
ks = 3
padding = "CONSTANT"
pad_input = tf.pad(inputgen, [[0, 0], [ks, ks], [ks, ks], [0, 0]], padding)
o_c1 = layers.general_conv2d_ga(pad_input, ngf, f, f, 1, 1, 0.02, name="c1", norm_type='Ins')
o_c2 = layers.general_conv2d_ga(o_c1, ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c2", norm_type='Ins')
o_c3 = layers.general_conv2d_ga(o_c2, ngf * 4, ks, ks, 2, 2, 0.02, "SAME", "c3", norm_type='Ins')
o_r1 = build_resnet_block_ins(o_c3, ngf * 4, "r1", padding)
o_r2 = build_resnet_block_ins(o_r1, ngf * 4, "r2", padding)
o_r3 = build_resnet_block_ins(o_r2, ngf * 4, "r3", padding)
o_r4 = build_resnet_block_ins(o_r3, ngf * 4, "r4", padding)
o_r5 = build_resnet_block_ins(o_r4, ngf * 4, "r5", padding)
o_r6 = build_resnet_block_ins(o_r5, ngf * 4, "r6", padding)
o_r7 = build_resnet_block_ins(o_r6, ngf * 4, "r7", padding)
o_r8 = build_resnet_block_ins(o_r7, ngf * 4, "r8", padding)
o_r9 = build_resnet_block_ins(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", norm_type='Ins')
o_c5 = layers.general_deconv2d(o_c4, [BATCH_SIZE, 256, 256, ngf], ngf, ks, ks, 2, 2, 0.02, "SAME", "c5", norm_type='Ins')
o_c6 = layers.general_conv2d_ga(o_c5, 1, f, f, 1, 1, 0.02, "SAME", "c6", do_norm=False, do_relu=False)
if skip is True:
out_gen = tf.nn.tanh(inputimg + o_c6, "t1")
else:
out_gen = tf.nn.tanh(o_c6, "t1")
return out_gen
def build_generator_resnet_9blocks(inputgen, name="generator", skip=False):
with tf.variable_scope(name):
f = 7
ks = 3
padding = "CONSTANT"
pad_input = tf.pad(inputgen, [[0, 0], [ks, ks], [
ks, ks], [0, 0]], padding)
#pad_input.shape = (1, 134, 134, 3)
o_c1 = layers.general_conv2d(
pad_input, ngf, f, f, 1, 1, 0.02, name="c1")
#o_c1.shape = (1, 128, 128, 32)
o_c2 = layers.general_conv2d(
o_c1, ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c2")
#o_c2.shape = (1, 64, 64, 64)
o_c3 = layers.general_conv2d(
o_c2, ngf * 4, ks, ks, 2, 2, 0.02, "SAME", "c3")
#o_c3.shape = (1, 32, 32, 128)
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_r9.shape = (1, 32, 32, 128)
o_d1 = layers.general_deconv2d(
o_r9, [BATCH_SIZE, 14, 14, ngf * 2], ngf * 2, ks, ks, 2, 2, 0.02,
"SAME", "d1")
#o_c5.shape = (1, 64, 64, 64)
o_d2 = layers.general_deconv2d(
o_d1, [BATCH_SIZE, 28, 28, ngf], ngf, ks, ks, 2, 2, 0.02,
"SAME", "d2")
#o_c5.shape = (1, 128, 128, 32)
o_c5 = layers.general_conv2d(o_d2, IMG_CHANNELS, f, f, 1, 1,
0.02, "SAME", "c5",
do_norm=False, do_relu=False)
#o_c6.shape = (1, 128, 128, 3)
if skip is True:
out_gen = tf.nn.tanh(inputgen + o_c5, "t1")
else:
out_gen = tf.nn.tanh(o_c5, "t1")
return out_gen
def build_decodernewb(o_r4, inputimg, name='decoder', skip=False):
with tf.variable_scope(name):
f = 7
ks = 3
o_c3 = layers.general_deconv2d(o_r4, [BATCH_SIZE, 64, 64, ngf * 2], ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c3", norm_type='Ins')
o_c4 = layers.general_deconv2d(o_c3, [BATCH_SIZE, 128, 128, ngf * 2], ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c4", norm_type='Ins')
o_c5 = layers.general_deconv2d(o_c4, [BATCH_SIZE, 256, 256, ngf], ngf, ks, ks, 2, 2, 0.02, "SAME", "c5", norm_type='Ins')
o_c6 = layers.general_conv2d(o_c5, 1, f, f, 1, 1, 0.02, "SAME", "c6", do_norm=False, do_relu=False)
if skip is True:
out_gen = tf.nn.tanh(inputimg + o_c6, "t1")
else:
out_gen = tf.nn.tanh(o_c6, "t1")
return out_gen
def build_segmenternew(inputse, name='segmenter',keep_rate=0.75):
with tf.variable_scope(name):
f = 7
ks = 3
padding = "CONSTANT"
o_c1 = layers.general_conv2d(inputse, ngf * 4, ks, ks, 1, 1, 0.02, "SAME", "c1", norm_type='Ins',keep_rate=keep_rate)
o_r1 = build_resnet_block(o_c1, ngf * 4, "r1", padding, norm_type='Ins')
o_r2 = build_resnet_block(o_r1, ngf * 4, "r2", padding, norm_type='Ins')
o_r3 = build_resnet_block(o_r2, ngf * 4, "r3", padding, norm_type='Ins')
o_r4 = build_resnet_block(o_r3, ngf * 4, "r4", padding, norm_type='Ins')
o_c3 = layers.general_deconv2d(o_r4, [BATCH_SIZE, 64, 64, ngf * 2], ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c3", norm_type='Ins')
o_c4 = layers.general_deconv2d(o_c3, [BATCH_SIZE, 128, 128, ngf * 2], ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c4", norm_type='Ins')
o_c5 = layers.general_deconv2d(o_c4, [BATCH_SIZE, 256, 256, ngf], ngf, ks, ks, 2, 2, 0.02, "SAME", "c5", norm_type='Ins')
o_c6 = layers.general_conv2d(o_c5, 4, f, f, 1, 1, 0.02, "SAME", "c6", do_norm=False, do_relu=False)
return o_c6
def build_generator_resnet_9blocks(inputgen, 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)
o_c1 = layers.general_conv2d(
inputgen, tf.constant(True, dtype=bool), ngf, f, f, 1, 1, 0.02, name="c1")
o_c2 = layers.general_conv2d(
o_c1, tf.constant(True, dtype=bool), ngf * 2, ks, ks, 2, 2, 0.02, padding='same', name="c2")
o_c3 = layers.general_conv2d(
o_c2, tf.constant(True, dtype=bool), ngf * 4, ks, ks, 2, 2, 0.02, padding='same', name="c3")
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, tf.constant(False, dtype=bool), IMG_CHANNELS, f, f, 1, 1,
0.02, "SAME", "c6", 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 build_generator_resnet_9blocks(inputgen, name="generator"):
with tf.variable_scope(name):
f = 7
ks = 3
pad_input = tf.pad(inputgen, [[0, 0], [ks, ks], [ks, ks], [0, 0]],
"REFLECT")
o_c1 = general_conv2d(pad_input, ngf, f, f, 1, 1, 0.02, name="c1")
o_c2 = general_conv2d(o_c1, ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c2")
o_c3 = general_conv2d(o_c2, ngf * 4, ks, ks, 2, 2, 0.02, "SAME", "c3")
o_r1 = build_resnet_block(o_c3, ngf * 4, "r1")
o_r2 = build_resnet_block(o_r1, ngf * 4, "r2")
o_r3 = build_resnet_block(o_r2, ngf * 4, "r3")
o_r4 = build_resnet_block(o_r3, ngf * 4, "r4")
o_r5 = build_resnet_block(o_r4, ngf * 4, "r5")
o_r6 = build_resnet_block(o_r5, ngf * 4, "r6")
o_r7 = build_resnet_block(o_r6, ngf * 4, "r7")
o_r8 = build_resnet_block(o_r7, ngf * 4, "r8")
o_r9 = build_resnet_block(o_r8, ngf * 4, "r9")
o_c4 = general_deconv2d(o_r9, [batch_size, 128, 128, ngf * 2], ngf * 2,
ks, ks, 2, 2, 0.02, "SAME", "c4")
o_c5 = general_deconv2d(o_c4, [batch_size, 256, 256, ngf], ngf, ks, ks,
2, 2, 0.02, "SAME", "c5")
o_c6 = general_conv2d(o_c5,
img_layer,
f,
f,
1,
1,
0.02,
"SAME",
"c6",
do_relu=False)
# Adding the tanh layer
out_gen = tf.nn.tanh(o_c6, "t1")
return out_gen
def build_decoder(inputde, inputimg, name='decoder', skip=False):
with tf.variable_scope(name):
f = 7
ks = 3
padding = "CONSTANT"
o_c1 = layers.general_conv2d(inputde, ngf * 4, ks, ks, 1, 1, 0.02, "SAME", "c1", norm_type='Ins')
o_r1 = build_resnet_block(o_c1, ngf * 4, "r1", padding, norm_type='Ins')
o_r2 = build_resnet_block(o_r1, ngf * 4, "r2", padding, norm_type='Ins')
o_r3 = build_resnet_block(o_r2, ngf * 4, "r3", padding, norm_type='Ins')
o_r4 = build_resnet_block(o_r3, ngf * 4, "r4", padding, norm_type='Ins')
o_c3 = layers.general_deconv2d(o_r4, [BATCH_SIZE, 64, 64, ngf * 2], ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c3", norm_type='Ins')
o_c4 = layers.general_deconv2d(o_c3, [BATCH_SIZE, 128, 128, ngf * 2], ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c4", norm_type='Ins')
o_c5 = layers.general_deconv2d(o_c4, [BATCH_SIZE, 256, 256, ngf], ngf, ks, ks, 2, 2, 0.02, "SAME", "c5", norm_type='Ins')
o_c6 = layers.general_conv2d(o_c5, 1, f, f, 1, 1, 0.02, "SAME", "c6", do_norm=False, do_relu=False)
if skip is True:
out_gen = tf.nn.tanh(inputimg + o_c6, "t1")
else:
out_gen = tf.nn.tanh(o_c6, "t1")
return out_gen
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 dehaze_resize_with_deconv(inputgen, name="generator", skip=False):
with tf.variable_scope(name):
f = 7
ks = 3
padding = "REFLECT"
pad_input = tf.pad(inputgen, [[0, 0], [ks, ks], [ks, ks], [0, 0]],
padding)
o_c1 = layers.general_conv2d(pad_input,
ngf,
f,
f,
1,
1,
0.02,
name="c1",
relufactor=0.2) #256*256*32
o_c2 = layers.general_conv2d(o_c1,
ngf * 2,
ks,
ks,
2,
2,
0.02,
"SAME",
"c2",
relufactor=0.2) #128*128*64
o_c3 = layers.general_conv2d(o_c2,
ngf * 4,
ks,
ks,
2,
2,
0.02,
"SAME",
"c3",
relufactor=0.2) #64*64*128
o_r1 = build_resnet_block(o_c3, ngf * 4, "r1", padding) #64*64*128
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)
with tf.variable_scope("resize_conv1"):
o_c4_0 = tf.concat([o_r9, o_c3], 3)
o_c4_1 = layers.instance_norm(o_c4_0)
o_c4_1 = layers.deconv2d_resize(o_c4_1,
ngf * 4,
kernel=ks,
stride=(2, 2),
name='deconv_1')
o_c4_1 = layers.lrelu(o_c4_1)
o_c4_2 = layers.general_deconv2d(o_c4_0,
[BATCH_SIZE, 128, 128, ngf * 2],
ngf * 2, ks, ks, 2, 2, 0.02,
"SAME", "c4")
o_c4_3 = tf.concat([o_c4_1, o_c4_2], 3)
o_c4_4 = layers.one_conv(o_c4_3, 64)
o_c4_4 = layers.lrelu(o_c4_4)
with tf.variable_scope("resize_conv2"):
o_c5_0 = tf.concat([o_c2, o_c4_4], 3)
o_c5 = layers.instance_norm(o_c5_0)
o_c5_1 = layers.deconv2d_resize(o_c5,
ngf * 2,
kernel=ks,
stride=(2, 2),
name='deconv_2')
o_c5_1 = layers.lrelu(o_c5_1)
o_c5_2 = layers.general_deconv2d(o_c5_0,
[BATCH_SIZE, 256, 256, ngf], ngf,
ks, ks, 2, 2, 0.02, "SAME", "c5")
o_c5_3 = tf.concat([o_c5_1, o_c5_2], 3)
o_c5_4 = layers.one_conv(o_c5_3, 32)
o_c5_4 = layers.lrelu(o_c5_4)
with tf.variable_scope("Output_layer"):
# o_c6_0 = tf.concat([o_c5_1, o_c5_2],3)
o_c6 = layers.general_conv2d(o_c5_4,
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 build_generator_resnet_9blocks_tf(inputgen,
inputref,
name="generator",
skip=False):
with tf.variable_scope(name):
f = 7
ks = 3
padding = "REFLECT"
pad_input = tf.pad(inputgen, [[0, 0], [ks, ks], [ks, ks], [0, 0]],
padding)
o_c1 = layers.general_conv2d(pad_input,
ngf,
f,
f,
1,
1,
0.02,
name="c1")
o_c2 = layers.general_conv2d(o_c1, ngf * 2, ks, ks, 2, 2, 0.02, "SAME",
"c2")
o_c3 = layers.general_conv2d(o_c2, ngf * 4, ks, ks, 2, 2, 0.02, "SAME",
"c3")
pad_input_ref = tf.pad(inputref, [[0, 0], [ks, ks], [ks, ks], [0, 0]],
padding)
o_ref_c1 = layers.general_conv2d(pad_input_ref,
ngf,
f,
f,
1,
1,
0.02,
name="ref_c1")
o_ref_c2 = layers.general_conv2d(o_ref_c1, ngf * 2, ks, ks, 2, 2, 0.02,
"SAME", "ref_c2")
o_ref_c3 = layers.general_conv2d(o_ref_c2, ngf * 4, ks, ks, 2, 2, 0.02,
"SAME", "ref_c3")
o_c_concat = tf.concat([o_c3, o_ref_c3], -1)
o_r1 = build_resnet_block(o_c_concat, ngf * 8, "r1", padding)
o_r2 = build_resnet_block(o_r1, ngf * 8, "r2", padding)
o_r3 = build_resnet_block(o_r2, ngf * 8, "r3", padding)
o_r4 = build_resnet_block(o_r3, ngf * 8, "r4", padding)
o_r5 = build_resnet_block(o_r4, ngf * 8, "r5", padding)
o_r6 = build_resnet_block(o_r5, ngf * 8, "r6", padding)
o_r7 = build_resnet_block(o_r6, ngf * 8, "r7", padding)
o_r8 = build_resnet_block(o_r7, ngf * 8, "r8", padding)
o_r9 = build_resnet_block(o_r8, ngf * 8, "r9", padding)
o_c4 = layers.general_deconv2d(o_r9, [BATCH_SIZE, 70, 121, ngf * 2],
ngf * 2, ks, ks, 2, 2, 0.02, "SAME",
"c4")
o_c5 = layers.general_deconv2d(o_c4, [BATCH_SIZE, 140, 242, 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 generator(inputA, edges, name="generator"):
f = 5
ks = 3
# padding = "REFLECT"
n_pool = 3
growth_rate = 8
n_layers_per_block = [2, 2, 2, 2, 2, 2, 2]
with tf.variable_scope(name):
n_filters = ngf
# skip_connection_list = []
o_c1 = layers.general_conv2d(inputA,
ngf,
f,
f,
1,
1,
0.02,
name="c1",
padding="SAME")
o_c2 = layers.general_conv2d(o_c1, ngf, ks, ks, 1, 1, 0.02, "SAME",
"c2")
o_c3 = layers.general_conv2d(o_c2, ngf, ks, ks, 1, 1, 0.02, "SAME",
"c3")
o_c4 = layers.general_deconv2d(o_c3, ngf, ks, ks, 2, 2, 0.02, "SAME",
"c4")
o_c4_1 = layers.general_conv2d(o_c4, ngf, ks, ks, 1, 1, 0.02, "SAME",
"c4_1")
o_c5 = layers.general_deconv2d(o_c4_1, ngf, ks, ks, 2, 2, 0.02, "SAME",
"c5")
o_c5_1 = layers.general_conv2d(o_c5, ngf, ks, ks, 1, 1, 0.02, "SAME",
"c5_1")
o_c6 = layers.general_deconv2d(o_c5_1, ngf * 2, ks, ks, 2, 2, 0.02,
"SAME", "c6")
stack = slim.conv2d(
o_c6,
ngf, [3, 3],
padding='SAME',
activation_fn=tf.nn.leaky_relu,
weights_initializer=tf.contrib.layers.variance_scaling_initializer(
factor=2.0, mode='FAN_IN', uniform=False))
stack, _ = DenseBlock(stack,
n_layers_per_block[0],
growth_rate,
scope='denseblock%d' % (1))
n_filters += growth_rate * n_layers_per_block[0]
out1 = tf.tile(tf.expand_dims(edges[:, :, :, 1], 3), [1, 1, 1, 48])
stack = tf.add(stack, out1)
stack, _ = DenseBlock(stack,
n_layers_per_block[1],
growth_rate,
scope='denseblock%d' % (2))
n_filters += growth_rate * n_layers_per_block[1]
out2 = tf.tile(tf.expand_dims(edges[:, :, :, 2], 3), [1, 1, 1, 64])
stack = tf.add(stack, out2)
stack, _ = DenseBlock(stack,
n_layers_per_block[2],
growth_rate,
scope='denseblock%d' % (3))
n_filters += growth_rate * n_layers_per_block[1]
stack, _ = DenseBlock(stack,
n_layers_per_block[n_pool],
growth_rate,
scope='denseblock%d' % (n_pool + 1))
out3 = tf.tile(tf.expand_dims(edges[:, :, :, 3], 3), [1, 1, 1, 96])
stack = tf.add(stack, out3)
stack, _ = DenseBlock(stack,
n_layers_per_block[n_pool + 1],
growth_rate,
scope='denseblock%d' % (n_pool + 2))
out4 = tf.tile(tf.expand_dims(edges[:, :, :, 4], 3), [1, 1, 1, 112])
stack = tf.add(stack, out4)
stack, _ = DenseBlock(stack,
n_layers_per_block[n_pool + 2],
growth_rate,
scope='denseblock%d' % (n_pool + 3))
out5 = tf.tile(tf.expand_dims(edges[:, :, :, 5], 3), [1, 1, 1, 128])
stack = tf.add(stack, out5)
stack, _ = DenseBlock(stack,
n_layers_per_block[n_pool + 3],
growth_rate,
scope='denseblock%d' % (n_pool + 4))
net = tf.nn.tanh(
layers.general_conv2d(stack,
1,
3,
3,
1,
1,
0.02,
"SAME",
"c6",
do_norm=False,
do_relu=False))
net = (net + tf.image.resize_images(
inputA, tf.shape(net)[1:3], align_corners=True)) / 2.0
return net
def build_generator_resnet_9blocks_tf(inputgen, name="generator", skip=False):
with tf.variable_scope(name):
f = 7
ks = 3
padding = "REFLECT"
#tf.pad()只是一种补齐的方式而已：可以参考http://m.blog.csdn.net/zhang_bei_qing/article/details/75090203
pad_input = tf.pad(inputgen, [[0, 0], [ks, ks], [ks, ks], [0, 0]],
padding)
#以下的三层卷积层，主要目的是提取出输入图像的主要特征（编码器）
#图像原输入为[256,256,3]--->[256,256,32]-->[128,128,64]-->[64,64,128]
o_c1 = layers.general_conv2d(pad_input,
ngf,
f,
f,
1,
1,
0.02,
name="c1")
o_c2 = layers.general_conv2d(o_c1, ngf * 2, ks, ks, 2, 2, 0.02, "SAME",
"c2")
o_c3 = layers.general_conv2d(o_c2, ngf * 4, ks, ks, 2, 2, 0.02, "SAME",
"c3")
#以下9层为转换器，这些网络的作用是组合图像的不同相近特性，然后基于这些
#特性，确定如何将图像的特征向量OAenc从DA域转换为DB域的特征向量
#o_r9表示转换层的最终输出，尺寸大小为：[64,64,128]可以看成是DB域中图像的特征向量
"""
build_resnet_block是一个由两个卷积层组成的神经网络层，其中部分输入数据直接添加到输出。
这样做是为了确保先前网络层的输入数据信息直接作用于后面的网络层，使得相应输出与原始输入的偏差缩小，
否则原始图像的特征将不会保留在输出中且输出结果会偏离目标轮廓。在上面也提到，这个任务的一个主要目标是保留原始图像的特征，
如目标的大小和形状，因此残差网络非常适合完成这些转换。
"""
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)
#以下3层为解码器，解码过程与编码方式完全相反，从特征向量中还原出低级特征，
# 这是利用了反卷积层（deconvolution）来完成的
#o_c6为最后的输出[1,256,256,3]
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 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_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
