How to use the ops.Residual function in ops
To help you get started, we’ve selected a few ops examples, based on popular ways it is used in public projects.
Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.
zhangqianhui / Sparsely-Grouped-GAN / SG_GAN.py View on Github 
with tf.variable_scope("encode_decode") as scope:
if reuse == True:
scope.reuse_variables()
conv1 = tf.nn.relu(
instance_norm(conv2d(x, output_dim=sn, k_w=7, k_h=7, d_w=1, d_h=1, name='e_c1'), scope='e_in1'))
conv2 = tf.nn.relu(
instance_norm(conv2d(conv1, output_dim=sn*2, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c2'), scope='e_in2'))
conv3 = tf.nn.relu(
instance_norm(conv2d(conv2, output_dim=sn*4, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c3'), scope='e_in3'))
r1 = Residual(conv3, residual_name='re_1')
r2 = Residual(r1, residual_name='re_2')
r3 = Residual(r2, residual_name='re_3')
r4 = Residual(r3, residual_name='re_4')
r5 = Residual(r4, residual_name='re_5')
r6 = Residual(r5, residual_name='re_6')
g_deconv1 = tf.nn.relu(instance_norm(de_conv(r6, output_shape=[self.batch_size,
self.output_size/2, self.output_size/2, sn*2], name='gen_deconv1'), scope="gen_in"))
# for 1
g_deconv_1_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,
output_shape=[self.batch_size, self.output_size, self.output_size, sn], name='g_deconv_1_1'), scope='gen_in_1_1'))
#Refined Residual Image learning
g_deconv_1_1_x = tf.concat([g_deconv_1_1, x], axis=3)
x_tilde1 = conv2d(g_deconv_1_1_x, output_dim=self.channel, k_w=7, k_h=7, d_h=1, d_w=1, name='gen_conv_1_2')
# for 2
g_deconv_2_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,print sn
with tf.variable_scope("encode_decode") as scope:
if reuse == True:
scope.reuse_variables()
conv1 = tf.nn.relu(
instance_norm(conv2d(x, output_dim=sn, k_w=7, k_h=7, d_w=1, d_h=1, name='e_c1'), scope='e_in1'))
conv2 = tf.nn.relu(
instance_norm(conv2d(conv1, output_dim=sn*2, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c2'), scope='e_in2'))
conv3 = tf.nn.relu(
instance_norm(conv2d(conv2, output_dim=sn*4, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c3'), scope='e_in3'))
r1 = Residual(conv3, residual_name='re_1')
r2 = Residual(r1, residual_name='re_2')
r3 = Residual(r2, residual_name='re_3')
r4 = Residual(r3, residual_name='re_4')
r5 = Residual(r4, residual_name='re_5')
r6 = Residual(r5, residual_name='re_6')
g_deconv1 = tf.nn.relu(instance_norm(de_conv(r6, output_shape=[self.batch_size,
self.output_size/2, self.output_size/2, sn*2], name='gen_deconv1'), scope="gen_in"))
# for 1
g_deconv_1_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,
output_shape=[self.batch_size, self.output_size, self.output_size, sn], name='g_deconv_1_1'), scope='gen_in_1_1'))
#Refined Residual Image learning
g_deconv_1_1_x = tf.concat([g_deconv_1_1, x], axis=3)
x_tilde1 = conv2d(g_deconv_1_1_x, output_dim=self.channel, k_w=7, k_h=7, d_h=1, d_w=1, name='gen_conv_1_2')with tf.variable_scope("encode_decode") as scope:
if reuse == True:
scope.reuse_variables()
x_var = tf.concat([x_var, img_mask, x_exemplar, exemplar_mask], axis=3)
conv1 = tf.nn.relu(
instance_norm(conv2d(x_var, output_dim=64, k_w=7, k_h=7, d_w=1, d_h=1, name='e_c1'), scope='e_in1'))
conv2 = tf.nn.relu(
instance_norm(conv2d(conv1, output_dim=128, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c2'), scope='e_in2'))
conv3 = tf.nn.relu(
instance_norm(conv2d(conv2, output_dim=256, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c3'), scope='e_in3'))
r1 = Residual(conv3, residual_name='re_1')
r2 = Residual(r1, residual_name='re_2')
r3 = Residual(r2, residual_name='re_3')
r4 = Residual(r3, residual_name='re_4')
r5 = Residual(r4, residual_name='re_5')
r6 = Residual(r5, residual_name='re_6')
g_deconv1 = tf.nn.relu(instance_norm(de_conv(r6, output_shape=[self.batch_size,
self.output_size/2, self.output_size/2, 128], name='gen_deconv1'), scope="gen_in"))
# for 1
g_deconv_1_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,
output_shape=[self.batch_size, self.output_size, self.output_size, 32], name='g_deconv_1_1'), scope='gen_in_1_1'))
g_deconv_1_1_x = tf.concat([g_deconv_1_1, x_var], axis=3)
x_tilde1 = conv2d(g_deconv_1_1_x, output_dim=self.channel, k_w=7, k_h=7, d_h=1, d_w=1, name='gen_conv_1_2')
return tf.nn.tanh(x_tilde1)scope.reuse_variables()
x_var = tf.concat([x_var, img_mask, x_exemplar, exemplar_mask], axis=3)
conv1 = tf.nn.relu(
instance_norm(conv2d(x_var, output_dim=64, k_w=7, k_h=7, d_w=1, d_h=1, name='e_c1'), scope='e_in1'))
conv2 = tf.nn.relu(
instance_norm(conv2d(conv1, output_dim=128, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c2'), scope='e_in2'))
conv3 = tf.nn.relu(
instance_norm(conv2d(conv2, output_dim=256, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c3'), scope='e_in3'))
r1 = Residual(conv3, residual_name='re_1')
r2 = Residual(r1, residual_name='re_2')
r3 = Residual(r2, residual_name='re_3')
r4 = Residual(r3, residual_name='re_4')
r5 = Residual(r4, residual_name='re_5')
r6 = Residual(r5, residual_name='re_6')
g_deconv1 = tf.nn.relu(instance_norm(de_conv(r6, output_shape=[self.batch_size,
self.output_size/2, self.output_size/2, 128], name='gen_deconv1'), scope="gen_in"))
# for 1
g_deconv_1_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,
output_shape=[self.batch_size, self.output_size, self.output_size, 32], name='g_deconv_1_1'), scope='gen_in_1_1'))
g_deconv_1_1_x = tf.concat([g_deconv_1_1, x_var], axis=3)
x_tilde1 = conv2d(g_deconv_1_1_x, output_dim=self.channel, k_w=7, k_h=7, d_h=1, d_w=1, name='gen_conv_1_2')
return tf.nn.tanh(x_tilde1)x_var = tf.concat([x_var, img_mask, x_exemplar, exemplar_mask], axis=3)
conv1 = tf.nn.relu(
instance_norm(conv2d(x_var, output_dim=64, k_w=7, k_h=7, d_w=1, d_h=1, name='e_c1'), scope='e_in1'))
conv2 = tf.nn.relu(
instance_norm(conv2d(conv1, output_dim=128, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c2'), scope='e_in2'))
conv3 = tf.nn.relu(
instance_norm(conv2d(conv2, output_dim=256, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c3'), scope='e_in3'))
r1 = Residual(conv3, residual_name='re_1')
r2 = Residual(r1, residual_name='re_2')
r3 = Residual(r2, residual_name='re_3')
r4 = Residual(r3, residual_name='re_4')
r5 = Residual(r4, residual_name='re_5')
r6 = Residual(r5, residual_name='re_6')
g_deconv1 = tf.nn.relu(instance_norm(de_conv(r6, output_shape=[self.batch_size,
self.output_size/2, self.output_size/2, 128], name='gen_deconv1'), scope="gen_in"))
# for 1
g_deconv_1_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,
output_shape=[self.batch_size, self.output_size, self.output_size, 32], name='g_deconv_1_1'), scope='gen_in_1_1'))
g_deconv_1_1_x = tf.concat([g_deconv_1_1, x_var], axis=3)
x_tilde1 = conv2d(g_deconv_1_1_x, output_dim=self.channel, k_w=7, k_h=7, d_h=1, d_w=1, name='gen_conv_1_2')
return tf.nn.tanh(x_tilde1)with tf.variable_scope("encode_decode") as scope:
if reuse == True:
scope.reuse_variables()
x_var = tf.concat([x_var, img_mask, x_exemplar, exemplar_mask], axis=3)
conv1 = tf.nn.relu(
instance_norm(conv2d(x_var, output_dim=64, k_w=7, k_h=7, d_w=1, d_h=1, name='e_c1'), scope='e_in1'))
conv2 = tf.nn.relu(
instance_norm(conv2d(conv1, output_dim=128, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c2'), scope='e_in2'))
conv3 = tf.nn.relu(
instance_norm(conv2d(conv2, output_dim=256, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c3'), scope='e_in3'))
r1 = Residual(conv3, residual_name='re_1')
r2 = Residual(r1, residual_name='re_2')
r3 = Residual(r2, residual_name='re_3')
r4 = Residual(r3, residual_name='re_4')
r5 = Residual(r4, residual_name='re_5')
r6 = Residual(r5, residual_name='re_6')
g_deconv1 = tf.nn.relu(instance_norm(de_conv(r6, output_shape=[self.batch_size,
self.output_size/2, self.output_size/2, 128], name='gen_deconv1'), scope="gen_in"))
# for 1
g_deconv_1_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,
output_shape=[self.batch_size, self.output_size, self.output_size, 32], name='g_deconv_1_1'), scope='gen_in_1_1'))
g_deconv_1_1_x = tf.concat([g_deconv_1_1, x_var], axis=3)
x_tilde1 = conv2d(g_deconv_1_1_x, output_dim=self.channel, k_w=7, k_h=7, d_h=1, d_w=1, name='gen_conv_1_2')
return tf.nn.tanh(x_tilde1)if reuse == True:
scope.reuse_variables()
conv1 = tf.nn.relu(
instance_norm(conv2d(x, output_dim=sn, k_w=7, k_h=7, d_w=1, d_h=1, name='e_c1'), scope='e_in1'))
conv2 = tf.nn.relu(
instance_norm(conv2d(conv1, output_dim=sn*2, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c2'), scope='e_in2'))
conv3 = tf.nn.relu(
instance_norm(conv2d(conv2, output_dim=sn*4, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c3'), scope='e_in3'))
r1 = Residual(conv3, residual_name='re_1')
r2 = Residual(r1, residual_name='re_2')
r3 = Residual(r2, residual_name='re_3')
r4 = Residual(r3, residual_name='re_4')
r5 = Residual(r4, residual_name='re_5')
r6 = Residual(r5, residual_name='re_6')
g_deconv1 = tf.nn.relu(instance_norm(de_conv(r6, output_shape=[self.batch_size,
self.output_size/2, self.output_size/2, sn*2], name='gen_deconv1'), scope="gen_in"))
# for 1
g_deconv_1_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,
output_shape=[self.batch_size, self.output_size, self.output_size, sn], name='g_deconv_1_1'), scope='gen_in_1_1'))
#Refined Residual Image learning
g_deconv_1_1_x = tf.concat([g_deconv_1_1, x], axis=3)
x_tilde1 = conv2d(g_deconv_1_1_x, output_dim=self.channel, k_w=7, k_h=7, d_h=1, d_w=1, name='gen_conv_1_2')
# for 2
g_deconv_2_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,
output_shape=[self.batch_size, self.output_size, self.output_size, sn]
, name='g_deconv_2_1'), scope='gen_in_2_1'))if reuse == True:
scope.reuse_variables()
x_var = tf.concat([x_var, img_mask, x_exemplar, exemplar_mask], axis=3)
conv1 = tf.nn.relu(
instance_norm(conv2d(x_var, output_dim=64, k_w=7, k_h=7, d_w=1, d_h=1, name='e_c1'), scope='e_in1'))
conv2 = tf.nn.relu(
instance_norm(conv2d(conv1, output_dim=128, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c2'), scope='e_in2'))
conv3 = tf.nn.relu(
instance_norm(conv2d(conv2, output_dim=256, k_w=4, k_h=4, d_w=2, d_h=2, name='e_c3'), scope='e_in3'))
r1 = Residual(conv3, residual_name='re_1')
r2 = Residual(r1, residual_name='re_2')
r3 = Residual(r2, residual_name='re_3')
r4 = Residual(r3, residual_name='re_4')
r5 = Residual(r4, residual_name='re_5')
r6 = Residual(r5, residual_name='re_6')
g_deconv1 = tf.nn.relu(instance_norm(de_conv(r6, output_shape=[self.batch_size,
self.output_size/2, self.output_size/2, 128], name='gen_deconv1'), scope="gen_in"))
# for 1
g_deconv_1_1 = tf.nn.relu(instance_norm(de_conv(g_deconv1,
output_shape=[self.batch_size, self.output_size, self.output_size, 32], name='g_deconv_1_1'), scope='gen_in_1_1'))
g_deconv_1_1_x = tf.concat([g_deconv_1_1, x_var], axis=3)
x_tilde1 = conv2d(g_deconv_1_1_x, output_dim=self.channel, k_w=7, k_h=7, d_h=1, d_w=1, name='gen_conv_1_2')
return tf.nn.tanh(x_tilde1)
