def __call__(self, EC_input):
"""
Args:
input: batch_size x width x height x 3
Returns:
output: same size as input
"""
with tf.variable_scope(self.name):
EC_input = tf.nn.dropout(EC_input, keep_prob=self.keep_prob)
with tf.variable_scope("conv1", reuse=self.reuse):
conv1 = tf.layers.conv2d(
inputs=EC_input,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 1),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv1')
norm1 = ops._norm(conv1, self.is_training, self.norm)
relu1 = ops.relu(norm1)
with tf.variable_scope("conv2", reuse=self.reuse):
conv2 = tf.layers.conv2d(
inputs=relu1,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv2')
norm2 = ops._norm(conv2, self.is_training, self.norm)
relu2 = ops.relu(norm2)
# pool1
with tf.variable_scope("conv3", reuse=self.reuse):
conv3 = tf.layers.conv2d(
inputs=relu2,
filters=self.ngf,
kernel_size=3,
strides=self.slice_stride,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv3')
# norm3 = ops._norm(conv3, self.is_training, self.norm)
# relu3 = ops.relu(norm3)
with tf.variable_scope("conv4", reuse=self.reuse):
conv4 = tf.layers.conv2d(
inputs=conv3,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv4')
norm4 = ops._norm(conv4, self.is_training, self.norm)
relu4 = ops.relu(norm4)
with tf.variable_scope("conv5", reuse=self.reuse):
conv5 = tf.layers.conv2d(
inputs=relu4,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv5')
norm5 = ops._norm(conv5, self.is_training, self.norm)
relu5 = tf.nn.relu(norm5)
# pool2
with tf.variable_scope("conv6", reuse=self.reuse):
conv6 = tf.layers.conv2d(
inputs=relu5,
filters=2 * self.ngf,
kernel_size=3,
strides=self.slice_stride,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv6')
# norm6 = ops._norm(conv6, self.is_training, self.norm)
# relu6 = ops.relu(norm6)
with tf.variable_scope("conv7", reuse=self.reuse):
conv7 = tf.layers.conv2d(
inputs=conv6,
filters=4 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv7')
norm7 = ops._norm(conv7, self.is_training, self.norm)
relu7 = ops.relu(norm7)
with tf.variable_scope("conv8", reuse=self.reuse):
conv8 = tf.layers.conv2d(
inputs=relu7,
filters=4 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv8')
norm8 = ops._norm(conv8, self.is_training, self.norm)
relu8 = ops.relu(norm8)
# pool3
with tf.variable_scope("conv9", reuse=self.reuse):
conv9 = tf.layers.conv2d(
inputs=relu8,
filters=4 * self.ngf,
kernel_size=3,
strides=self.slice_stride,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv9')
# DC
with tf.variable_scope("conv10", reuse=self.reuse):
conv10 = tf.layers.conv2d(
inputs=conv9,
filters=4 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv10')
norm10 = ops._norm(conv10, self.is_training, self.norm)
relu10 = ops.relu(norm10)
with tf.variable_scope("deconv1_r", reuse=self.reuse):
resize1 = ops.uk_resize(relu10,
reuse=self.reuse,
name='resize1')
deconv1_r = tf.layers.conv2d(
inputs=resize1,
filters=4 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv1_r')
deconv1_norm1_r = ops._norm(deconv1_r, self.is_training,
self.norm)
deconv1 = ops.relu(deconv1_norm1_r)
with tf.variable_scope("concat1", reuse=self.reuse):
concat1 = tf.concat([relu8, deconv1], axis=-1)
with tf.variable_scope("add1_conv1", reuse=self.reuse):
add1_conv1 = tf.layers.conv2d(
inputs=concat1,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 8 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add1_conv1')
add1_norm1 = ops._norm(add1_conv1, self.is_training, self.norm)
add1_relu1 = ops.relu(add1_norm1)
with tf.variable_scope("add1_conv2", reuse=self.reuse):
add1_conv2 = tf.layers.conv2d(
inputs=add1_relu1,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add1_conv2')
add1_norm2 = ops._norm(add1_conv2, self.is_training, self.norm)
add1_relu2 = ops.relu(add1_norm2)
with tf.variable_scope("deconv2_r", reuse=self.reuse):
resize2 = ops.uk_resize(add1_relu2,
reuse=self.reuse,
name='resize2')
deconv2_r = tf.layers.conv2d(
inputs=resize2,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv2_r')
deconv2_norm1_r = ops._norm(deconv2_r, self.is_training,
self.norm)
deconv2 = ops.relu(deconv2_norm1_r)
with tf.variable_scope("concat2", reuse=self.reuse):
concat2 = tf.concat([relu5, deconv2], axis=-1)
with tf.variable_scope("add2_conv1", reuse=self.reuse):
add2_conv1 = tf.layers.conv2d(
inputs=concat2,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add2_conv1')
add2_norm1 = ops._norm(add2_conv1, self.is_training, self.norm)
add2_relu1 = ops.relu(add2_norm1)
with tf.variable_scope("add2_conv2", reuse=self.reuse):
add2_conv = tf.layers.conv2d(
inputs=add2_relu1,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add2_conv2')
add2_norm2 = ops._norm(add2_conv, self.is_training, self.norm)
add2_relu2 = ops.relu(add2_norm2)
with tf.variable_scope("deconv3_r", reuse=self.reuse):
resize3 = ops.uk_resize(add2_relu2,
reuse=self.reuse,
name='resize3')
deconv3_r = tf.layers.conv2d(
inputs=resize3,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv3_r')
deconv3_norm1_r = ops._norm(deconv3_r, self.is_training,
self.norm)
deconv3 = ops.relu(deconv3_norm1_r)
with tf.variable_scope("concat2", reuse=self.reuse):
concat3 = tf.concat([relu2, deconv3], axis=-1)
with tf.variable_scope("add3_conv1", reuse=self.reuse):
add3_conv1 = tf.layers.conv2d(
inputs=concat3,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add3_conv1')
add3_norm1 = ops._norm(add3_conv1, self.is_training, self.norm)
add3_relu1 = ops.relu(add3_norm1)
with tf.variable_scope("add3_conv2", reuse=self.reuse):
add3_conv2 = tf.layers.conv2d(
inputs=add3_relu1,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add3_conv2')
add3_norm2 = ops._norm(add3_conv2, self.is_training, self.norm)
add3_relu2 = ops.relu(add3_norm2)
with tf.variable_scope("lastconv", reuse=self.reuse):
lastconv = tf.layers.conv2d(
inputs=add3_relu2,
filters=self.output_channl,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='lastconv')
lastnorm = ops._norm(lastconv, self.is_training, self.norm)
output = tf.nn.sigmoid(lastnorm)
self.reuse = True
self.variables = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES,
scope=self.name)
return output
def __call__(self, EC_input):
"""
Args:
input: batch_size x width x height x 3
Returns:
output: same size as input
"""
with tf.variable_scope(self.name):
EC_input = tf.nn.dropout(EC_input, keep_prob=self.keep_prob)
with tf.variable_scope("conv1", reuse=self.reuse):
conv1 = tf.layers.conv2d(
inputs=EC_input,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv1')
# norm1 = ops._norm(conv1, self.is_training, self.norm)
relu1 = ops.relu(conv1)
with tf.variable_scope("conv2", reuse=self.reuse):
conv2 = tf.layers.conv2d(
inputs=relu1,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv2')
# norm2 = ops._norm(conv2, self.is_training, self.norm)
relu2 = ops.relu(conv2)
# pool1
with tf.variable_scope("conv3", reuse=self.reuse):
conv3 = tf.layers.conv2d(
inputs=relu2,
filters=2 * self.ngf,
kernel_size=3,
strides=self.slice_stride,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv3')
# norm3 = ops._norm(conv3, self.is_training, self.norm)
relu3 = ops.relu(conv3)
with tf.variable_scope("conv4", reuse=self.reuse):
conv4 = tf.layers.conv2d(
inputs=relu3,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv4')
# norm4 = ops._norm(conv4, self.is_training, self.norm)
relu4 = ops.relu(conv4)
with tf.variable_scope("conv5", reuse=self.reuse):
conv5 = tf.layers.conv2d(
inputs=relu4,
filters=4 * self.ngf,
kernel_size=3,
strides=self.slice_stride,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv5')
# norm5 = ops._norm(conv5, self.is_training, self.norm)
relu5 = tf.nn.relu(conv5)
"""
decoder
"""
with tf.variable_scope("conv6", reuse=self.reuse):
conv6 = tf.layers.conv2d(
inputs=relu5,
filters=4 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv6')
# add1_norm1 = ops._norm(add1_conv1, self.is_training, self.norm)
relu6 = ops.relu(conv6)
with tf.variable_scope("deconv7_r", reuse=self.reuse):
resize1 = ops.uk_resize(relu6,
reuse=self.reuse,
name='resize1')
deconv7_r = tf.layers.conv2d(
inputs=resize1,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv7_r')
# deconv1_norm1_r = ops._norm(deconv1_r, self.is_training, self.norm)
deconv7_r += relu4
deconv7 = ops.relu(deconv7_r)
with tf.variable_scope("conv8", reuse=self.reuse):
conv8 = tf.layers.conv2d(
inputs=deconv7,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv8')
# add1_norm2 = ops._norm(add1_conv2, self.is_training, self.norm)
relu8 = ops.relu(conv8)
with tf.variable_scope("deconv9_r", reuse=self.reuse):
resize2 = ops.uk_resize(relu8,
reuse=self.reuse,
name='resize2')
deconv9_r = tf.layers.conv2d(
inputs=resize2,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv9_r')
# deconv2_norm1_r = ops._norm(deconv2_r, self.is_training, self.norm)
deconv9_r += relu2
deconv9 = ops.relu(deconv9_r)
with tf.variable_scope("conv10", reuse=self.reuse):
conv10 = tf.layers.conv2d(
inputs=deconv9,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv10')
# add2_norm1 = ops._norm(add2_conv1, self.is_training, self.norm)
relu10 = ops.relu(conv10)
with tf.variable_scope("lastconv", reuse=self.reuse):
lastconv = tf.layers.conv2d(
inputs=relu10,
filters=self.output_channl,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
stddev=0.01, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='lastconv')
output = tf.nn.sigmoid(lastconv)
self.reuse = True
self.variables = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES,
scope=self.name)
return output
def __call__(self, DC_input):
"""
Args:
input: batch_size x width x height x N
Returns:
output: same size as input
"""
with tf.variable_scope(self.name, reuse=self.reuse):
with tf.variable_scope("dense0", reuse=self.reuse):
dense0 = tf.layers.dense(
DC_input,
units=DC_input.get_shape().as_list()[0] * 6 * 5 * self.ngf,
name="dense0")
with tf.variable_scope("dense1", reuse=self.reuse):
dense1 = tf.layers.dense(
dense0,
units=DC_input.get_shape().as_list()[0] * 6 * 5 * 12 *
self.ngf,
name="dense0")
dense1 = tf.reshape(dense1,
shape=[
DC_input.get_shape().as_list()[0], 6,
5, 12 * self.ngf
])
# 6,5
with tf.variable_scope("conv0_1", reuse=self.reuse):
conv0_1 = tf.layers.conv2d(
inputs=dense1,
filters=12 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 12 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv0_1')
norm0_1 = ops._norm(conv0_1, self.is_training, self.norm)
relu0_1 = ops.relu(norm0_1)
# 6,5
with tf.variable_scope("deconv0_1_r", reuse=self.reuse):
resize0_1 = ops.uk_resize(relu0_1,
reuse=self.reuse,
output_size=[12, 9],
name='resize')
deconv0_1_r = tf.layers.conv2d(
inputs=resize0_1,
filters=8 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 12 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv0_1_r')
deconv0_1_norm1_r = ops._norm(deconv0_1_r, self.is_training,
self.norm)
deconv0_1_relu1 = ops.relu(deconv0_1_norm1_r)
# 12,9
with tf.variable_scope("conv0_2", reuse=self.reuse):
conv0_2 = tf.layers.conv2d(
inputs=deconv0_1_relu1,
filters=8 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 8 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv0_2')
norm0_2 = ops._norm(conv0_2, self.is_training, self.norm)
relu0_2 = ops.relu(norm0_2)
# 12,9
with tf.variable_scope("deconv0_2_r", reuse=self.reuse):
resize0_2 = ops.uk_resize(relu0_2,
reuse=self.reuse,
output_size=[23, 18],
name='resize')
deconv0_2_r = tf.layers.conv2d(
inputs=resize0_2,
filters=6 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 8 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv0_2_r')
deconv0_2_norm1_r = ops._norm(deconv0_2_r, self.is_training,
self.norm)
deconv0_2_relu1 = ops.relu(deconv0_2_norm1_r)
# 23, 18
with tf.variable_scope("conv0_3", reuse=self.reuse):
conv0_3 = tf.layers.conv2d(
inputs=deconv0_2_relu1,
filters=6 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 6 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv0_3')
norm0_3 = ops._norm(conv0_3, self.is_training, self.norm)
relu0_3 = ops.relu(norm0_3)
# 23, 18
with tf.variable_scope("deconv0_3_r", reuse=self.reuse):
resize0_3 = ops.uk_resize(relu0_3,
reuse=self.reuse,
name='resize')
deconv0_3_r = tf.layers.conv2d(
inputs=resize0_3,
filters=6 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 6 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv0_3_r')
deconv0_3_norm1_r = ops._norm(deconv0_3_r, self.is_training,
self.norm)
add0 = ops.relu(deconv0_3_norm1_r)
# 46, 36
with tf.variable_scope("conv1", reuse=self.reuse):
conv1 = tf.layers.conv2d(
inputs=add0,
filters=6 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 6 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv1')
norm1 = ops._norm(conv1, self.is_training, self.norm)
relu1 = ops.relu(norm1)
with tf.variable_scope("deconv1_r", reuse=self.reuse):
resize1 = ops.uk_resize(relu1, reuse=self.reuse, name='resize')
deconv1_r = tf.layers.conv2d(
inputs=resize1,
filters=4 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 6 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv1_r')
deconv1_norm1_r = ops._norm(deconv1_r, self.is_training,
self.norm)
add1 = ops.relu(deconv1_norm1_r)
with tf.variable_scope("add1_conv1", reuse=self.reuse):
add1_conv1 = tf.layers.conv2d(
inputs=add1,
filters=4 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add1_conv1')
add1_norm1 = ops._norm(add1_conv1, self.is_training, self.norm)
add1_relu1 = ops.relu(add1_norm1)
with tf.variable_scope("add1_conv2", reuse=self.reuse):
add1_conv2 = tf.layers.conv2d(
inputs=add1_relu1,
filters=4 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add1_conv2')
add1_norm2 = ops._norm(add1_conv2, self.is_training, self.norm)
add1_relu2 = ops.relu(add1_norm2)
with tf.variable_scope("deconv2_r", reuse=self.reuse):
resize2 = ops.uk_resize(add1_relu2,
reuse=self.reuse,
name='resize')
deconv2_r = tf.layers.conv2d(
inputs=resize2,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv2_r')
deconv2_norm1_r = ops._norm(deconv2_r, self.is_training,
self.norm)
add2 = ops.relu(deconv2_norm1_r)
with tf.variable_scope("add2_conv1", reuse=self.reuse):
add2_conv1 = tf.layers.conv2d(
inputs=add2,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add2_conv1')
add2_norm1 = ops._norm(add2_conv1, self.is_training, self.norm)
add2_relu1 = ops.relu(add2_norm1)
with tf.variable_scope("add2_conv2", reuse=self.reuse):
add2_conv = tf.layers.conv2d(
inputs=add2_relu1,
filters=2 * self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add2_conv2')
add2_norm2 = ops._norm(add2_conv, self.is_training, self.norm)
add2_relu2 = ops.relu(add2_norm2)
with tf.variable_scope("conv2", reuse=self.reuse):
conv2 = tf.layers.conv2d(
inputs=add2_relu2,
filters=self.ngf,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='conv2')
norm2 = ops._norm(conv2, self.is_training, self.norm)
relu2 = ops.relu(norm2)
with tf.variable_scope("lastconv", reuse=self.reuse):
lastconv = tf.layers.conv2d(
inputs=relu2,
filters=self.output_channl,
kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * self.ngf),
stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='lastconv')
lastnorm = ops._norm(lastconv, self.is_training, self.norm)
output = tf.nn.sigmoid(lastnorm)
self.reuse = True
self.variables = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES,
scope=self.name)
return output
def __call__(self, DC_input):
"""
Args:
input: batch_size x width x height x N
Returns:
output: same size as input
"""
with tf.variable_scope(self.name, reuse=self.reuse):
DC_input = tf.nn.dropout(DC_input, keep_prob=self.keep_prob)
with tf.variable_scope("conv1", reuse=self.reuse):
conv1 = tf.layers.conv2d(inputs=DC_input, filters=8 * self.ngf, kernel_size=3, strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 8 * self.ngf), stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0), name='conv1')
norm1 = ops.norm(conv1)
relu1 = ops.relu(norm1)
with tf.variable_scope("deconv1_r", reuse=self.reuse):
resize1 = ops.uk_resize(relu1, reuse=self.reuse, name='resize1')
deconv1_r = tf.layers.conv2d(inputs=resize1, filters=4 * self.ngf, kernel_size=3, strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 8 * self.ngf), stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv1_r')
deconv1_norm1_r = ops.norm(deconv1_r)
add1 = ops.relu(deconv1_norm1_r)
with tf.variable_scope("add1_conv1", reuse=self.reuse):
add1_conv1 = tf.layers.conv2d(inputs=add1, filters=4 * self.ngf, kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf), stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add1_conv1')
add1_norm1 = ops.norm(add1_conv1)
add1_relu1 = ops.relu(add1_norm1)
with tf.variable_scope("add1_conv2", reuse=self.reuse):
add1_conv2 = tf.layers.conv2d(inputs=add1_relu1, filters=4 * self.ngf, kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf), stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add1_conv2')
add1_norm2 = ops.norm(add1_conv2)
add1_relu2 = ops.relu(add1_norm2)
with tf.variable_scope("deconv2_r", reuse=self.reuse):
resize2 = ops.uk_resize(add1_relu2, reuse=self.reuse, name='resize1')
deconv2_r = tf.layers.conv2d(inputs=resize2, filters=2 * self.ngf, kernel_size=3, strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 4 * self.ngf), stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='deconv2_r')
deconv2_norm1_r = ops.norm(deconv2_r)
add2 = ops.relu(deconv2_norm1_r)
with tf.variable_scope("add2_conv1", reuse=self.reuse):
add2_conv1 = tf.layers.conv2d(inputs=add2, filters=2 * self.ngf, kernel_size=3,
strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf), stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add2_conv1')
add2_norm1 = ops.norm(add2_conv1)
add2_relu1 = ops.relu(add2_norm1)
with tf.variable_scope("add2_conv2", reuse=self.reuse):
add2_conv = tf.layers.conv2d(inputs=add2_relu1, filters=2 * self.ngf, kernel_size=3, strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf), stddev=0.000001,
dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0),
name='add2_conv2')
add2_norm2 = ops.norm(add2_conv)
add2_relu2 = ops.relu(add2_norm2)
with tf.variable_scope("conv2", reuse=self.reuse):
conv2 = tf.layers.conv2d(inputs=add2_relu2, filters=self.ngf, kernel_size=3, strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * 2 * self.ngf), stddev=0.000001, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0), name='conv2')
norm2 = ops.norm(conv2)
relu2 = ops.relu(norm2)
with tf.variable_scope("lastconv", reuse=self.reuse):
lastconv = tf.layers.conv2d(inputs=relu2, filters=self.output_channl, kernel_size=3, strides=1,
padding="SAME",
activation=None,
kernel_initializer=tf.random_normal_initializer(
mean=1.0 / (9.0 * self.ngf), stddev=0.000001, dtype=tf.float32),
bias_initializer=tf.constant_initializer(0.0), name='lastconv')
lastnorm = ops.norm(lastconv)
output = tf.nn.sigmoid(lastnorm)
self.reuse = True
self.variables = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=self.name)
return output