def discriminator(inputdisc, name="discriminator"):
with tf.variable_scope(name):
f = 4
padw = 2
pad_input = tf.pad(inputdisc, [[0, 0], [padw, padw], [
padw, padw], [0, 0]], "CONSTANT")
o_c1 = layers.general_conv2d(pad_input, model.ndf, f, f, 2, 2,
0.02, "VALID", "c1", do_norm=False,
relufactor=0.2)
pad_o_c1 = tf.pad(o_c1, [[0, 0], [padw, padw], [
padw, padw], [0, 0]], "CONSTANT")
o_c2 = layers.general_conv2d(pad_o_c1, model.ndf * 2, f, f, 2, 2,
0.02, "VALID", "c2", relufactor=0.2)
pad_o_c2 = tf.pad(o_c2, [[0, 0], [padw, padw], [
padw, padw], [0, 0]], "CONSTANT")
o_c3 = layers.general_conv2d(pad_o_c2, model.ndf * 4, f, f, 2, 2,
0.02, "VALID", "c3", relufactor=0.2)
pad_o_c3 = tf.pad(o_c3, [[0, 0], [padw, padw], [
padw, padw], [0, 0]], "CONSTANT")
o_c4 = layers.general_conv2d(pad_o_c3, model.ndf * 8, f, f, 1, 1,
0.02, "VALID", "c4", relufactor=0.2)
pad_o_c4 = tf.pad(o_c4, [[0, 0], [padw, padw], [
padw, padw], [0, 0]], "CONSTANT")
o_c5 = layers.general_conv2d(
pad_o_c4, 1, f, f, 1, 1, 0.02, "VALID", "c5",
do_norm=False, do_relu=False)
return o_c5
def patch_discriminator(inputdisc, name="discriminator"):
with tf.variable_scope(name):
f = 4
patch_input = tf.random_crop(inputdisc, [1, 70, 70, 3])
o_c1 = layers.general_conv2d(patch_input, model.ndf, f, f, 2, 2,
0.02, "SAME", "c1", do_norm="False",
relufactor=0.2)
o_c2 = layers.general_conv2d(o_c1, model.ndf * 2, f, f, 2, 2,
0.02, "SAME", "c2", relufactor=0.2)
o_c3 = layers.general_conv2d(o_c2, model.ndf * 4, f, f, 2, 2,
0.02, "SAME", "c3", relufactor=0.2)
o_c4 = layers.general_conv2d(o_c3, model.ndf * 8, f, f, 2, 2,
0.02, "SAME", "c4", relufactor=0.2)
o_c5 = layers.general_conv2d(
o_c4, 1, f, f, 1, 1, 0.02, "SAME", "c5", do_norm=False,
do_relu=False)
return o_c5
def discriminator_tf(inputdisc, name="discriminator"):
with tf.variable_scope(name):
f = 4
o_c1 = layers.general_conv2d(inputdisc, model.ndf, f, f, 2, 2,
0.02, "SAME", "c1", do_norm=False,
relufactor=0.2)
o_c2 = layers.general_conv2d(o_c1, model.ndf * 2, f, f, 2, 2,
0.02, "SAME", "c2", relufactor=0.2)
o_c3 = layers.general_conv2d(o_c2, model.ndf * 4, f, f, 2, 2,
0.02, "SAME", "c3", relufactor=0.2)
o_c4 = layers.general_conv2d(o_c3, model.ndf * 8, f, f, 1, 1,
0.02, "SAME", "c4", relufactor=0.2)
o_c5 = layers.general_conv2d(
o_c4, 1, f, f, 1, 1, 0.02,
"SAME", "c5", do_norm=False, do_relu=False
)
return o_c5
def build_resnet_block(inputres, dim, name="resnet", padding="REFLECT"):
"""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.
"""
with tf.variable_scope(name):
out_res = tf.pad(inputres, [[0, 0], [1, 1], [
1, 1], [0, 0]], padding)
out_res = layers.general_conv2d(
out_res, dim, 3, 3, 1, 1, 0.02, "VALID", "c1")
out_res = tf.pad(out_res, [[0, 0], [1, 1], [1, 1], [0, 0]], padding)
out_res = layers.general_conv2d(
out_res, dim, 3, 3, 1, 1, 0.02, "VALID", "c2", do_relu=False)
return tf.nn.relu(out_res + inputres)
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)
o_c1 = layers.general_conv2d(
pad_input, model.ngf, f, f, 1, 1, 0.02, name="c1")
o_c2 = layers.general_conv2d(
o_c1, model.ngf * 2, ks, ks, 2, 2, 0.02, "SAME", "c2")
o_c3 = layers.general_conv2d(
o_c2, model.ngf * 4, ks, ks, 2, 2, 0.02, "SAME", "c3")
o_r1 = model.build_resnet_block(o_c3, model.ngf * 4, "r1", padding)
o_r2 = model.build_resnet_block(o_r1, model.ngf * 4, "r2", padding)
o_r3 = model.build_resnet_block(o_r2, model.ngf * 4, "r3", padding)
o_r4 = model.build_resnet_block(o_r3, model.ngf * 4, "r4", padding)
o_r5 = model.build_resnet_block(o_r4, model.ngf * 4, "r5", padding)
o_r6 = model.build_resnet_block(o_r5, model.ngf * 4, "r6", padding)
o_r7 = model.build_resnet_block(o_r6, model.ngf * 4, "r7", padding)
o_r8 = model.build_resnet_block(o_r7, model.ngf * 4, "r8", padding)
o_r9 = model.build_resnet_block(o_r8, model.ngf * 4, "r9", padding)
o_c4 = layers.general_deconv2d(
o_r9, [model.BATCH_SIZE, 128, 128, model.ngf * 2], model.ngf * 2, ks, ks, 2, 2, 0.02,
"SAME", "c4")
o_c5 = layers.general_deconv2d(
o_c4, [model.BATCH_SIZE, 256, 256, model.ngf], model.ngf, ks, ks, 2, 2, 0.02,
"SAME", "c5")
o_c6 = layers.general_conv2d(o_c5, model.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