def decoder(self,input_z,name = 'generate_img',is_training = True):
hidden_num = 64
output_dim = 64
with tf.variable_scope(name,reuse = tf.AUTO_REUSE):
x = ly.fc(input_z, hidden_num * 8 * (output_dim // 16) * (output_dim // 16),name = 'gen_fc_0')
x = tf.reshape(x, shape=[self.imle_deep, output_dim // 16, output_dim // 16, hidden_num * 8]) ## 4, 4, 8*64
x = ly.deconv2d(x,hidden_num * 4,name = 'g_deconv2d_0') ### 8,8, 256
x = ly.batch_normal(x,name = 'g_deconv_bn_0',is_training = is_training)
x = ly.relu(x)
x = ly.deconv2d(x,hidden_num * 2,name = 'g_deconv2d_1') ### 16,16, 128
x = ly.batch_normal(x,name = 'g_deconv_bn_1',is_training = is_training)
x = ly.relu(x)
x = ly.deconv2d(x,hidden_num,name = 'g_deconv2d_2') ### 32,32, 64
x = ly.batch_normal(x,name = 'g_deconv_bn_2',is_training = is_training)
x = ly.relu(x)
x = ly.deconv2d(x, 3, name = 'g_deconv2d_3') ### 64,64, 3
x = ly.batch_normal(x,name = 'g_deconv_bn_3',is_training = is_training)
x = tf.nn.tanh(x)
return x
def discriminator(self,
x,
name='discriminator_img',
is_training=True): ## 64,64,3
with tf.variable_scope(name, reuse=tf.AUTO_REUSE):
x = ly.conv2d(x, 64, strides=2, use_bias=True,
name='d_conv_0') ## 32,32,64
x = ly.batch_normal(x, name='d_bn_0', is_training=is_training)
x = ly.relu(x, 0.2)
x = ly.conv2d(x, 128, strides=2, use_bias=True,
name='d_conv_1') ## 16,16,128
x = ly.batch_normal(x, name='d_bn_1', is_training=is_training)
x = ly.relu(x, 0.2)
x = ly.conv2d(x, 256, strides=2, use_bias=True,
name='d_conv_2') ## 8,8,256
x = ly.batch_normal(x, name='d_bn_2', is_training=is_training)
x = ly.relu(x, 0.2)
x = ly.conv2d(x, 512, strides=2, use_bias=True,
name='d_conv_3') ## 4,4,512
x = ly.batch_normal(x, name='d_bn_3', is_training=is_training)
x = ly.relu(x, 0.2)
x = ly.fc(x, 1, name='fc_0')
x = tf.nn.sigmoid(x)
return x
def __call__(self, input):
with tf.variable_scope(self.name, reuse=self.reuse):
input = ly.conv2d(input, 64, strides=2,
name='conv_0') ## (-1,150,150,64)
input = ly.batch_normal(input, name='bn_0')
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 128, strides=2,
name='conv_1') ## (-1,75,75,128)
input = ly.batch_normal(input, name='bn_1')
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 256, strides=2,
name='conv_2') ## (-1,38,38,256)
input = ly.batch_normal(input, name='bn_2')
input = tf.nn.leaky_relu(input)
input = ly.conv2d(input, 512, strides=2,
name='conv_3') ## (-1,19,19,512)
input = ly.batch_normal(input, name='bn_3')
input = tf.nn.leaky_relu(input)
print(input.shape)
input = ly.conv2d(input, 512, strides=2,
name='conv_4') ## (-1,10,10,512)
input = ly.batch_normal(input, name='bn_4')
input = tf.nn.leaky_relu(input)
## avg
input = tf.reduce_mean(input, axis=[1, 2])
input = tf.nn.dropout(input, keep_prob=0.5)
input = ly.fc(input, 1, name='fc_0')
# input = ly.batch_normal(input, name='bn_5')
input = tf.nn.sigmoid(input)
return input
def classify(self,
d_opt=None,
name='classify',
is_training=True): ### 64,64,1
with tf.variable_scope(name, reuse=tf.AUTO_REUSE):
x = tf.pad(self.input_img, [[0, 0], [5, 5], [5, 5], [0, 0]],
"REFLECT")
x = ly.conv2d(x,
64,
kernal_size=11,
name='conv_0',
padding='VALID',
use_bias=True)
x = ly.batch_normal(x, name='bn_0', is_training=is_training)
x = ly.relu(x)
x = ly.maxpooling2d(x) ## 32,32,64
x = tf.pad(x, [[0, 0], [3, 3], [3, 3], [0, 0]], "REFLECT")
x = ly.conv2d(x,
128,
kernal_size=7,
name='conv_1',
padding='VALID',
use_bias=True)
x = ly.batch_normal(x, name='bn_1', is_training=is_training)
x = ly.relu(x)
x = ly.maxpooling2d(x) ## 16,16,128
x = tf.pad(x, [[0, 0], [2, 2], [2, 2], [0, 0]], "REFLECT")
x = ly.conv2d(x,
256,
kernal_size=5,
name='conv_2',
padding='VALID',
use_bias=True)
x = ly.batch_normal(x, name='bn_2', is_training=is_training)
x = ly.relu(x)
x = ly.maxpooling2d(x) ## 8,8,256
x = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]], "REFLECT")
x = ly.conv2d(x,
512,
kernal_size=3,
name='conv_3',
padding='VALID',
use_bias=True)
x = ly.batch_normal(x, name='bn_3', is_training=is_training)
x = ly.relu(x)
x = tf.pad(x, [[0, 0], [1, 1], [1, 1], [0, 0]], "REFLECT")
x = ly.conv2d(x,
512,
kernal_size=3,
name='conv_4',
padding='VALID',
use_bias=True)
x = ly.batch_normal(x, name='bn_4', is_training=is_training)
x = ly.relu(x)
x = ly.maxpooling2d(x) ## 4,4,512
x = ly.fc(x, 1024, name='fc_0', use_bias=True)
x = ly.batch_normal(x, name='bn_5', is_training=is_training)
x = ly.relu(x)
x = tf.nn.dropout(x, keep_prob=0.5)
x = ly.fc(x, self.class_num, name='fc_1', use_bias=True)
self.pred_x_index = tf.argmax(tf.nn.softmax(x), axis=-1)
self.pred_x_value = tf.reduce_max(tf.nn.softmax(x), axis=-1)
if (is_training):
cross_loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits_v2(
labels=self.input_label, logits=x),
axis=0)
l2_loss = 0.0005 * tf.reduce_sum([
tf.nn.l2_loss(var)
for var in self.get_single_var('classify/fc')
])
loss = cross_loss + l2_loss
self.summaries.append(tf.summary.scalar('loss', loss))
_grad = d_opt.compute_gradients(
loss, var_list=self.get_vars('classify'))
train_op = d_opt.apply_gradients(_grad)
return train_op
def __call__(self, input):
with tf.variable_scope(self.name, reuse=self.reuse):
input = ly.conv2d(input,
64,
kernel_size=7,
strides=1,
name='g_conv2d_0')
input = ly.batch_normal(input, name='g_bn_0')
input = tf.nn.relu(input)
input = ly.conv2d(input,
128,
kernel_size=3,
strides=2,
name='g_conv2d_1')
input = ly.batch_normal(input, name='g_bn_1')
input = tf.nn.relu(input)
input = ly.conv2d(input,
256,
kernel_size=3,
strides=2,
name='g_conv2d_2')
input = ly.batch_normal(input, name='g_bn_2')
input = tf.nn.relu(input)
### resnet
for i in range(8):
cell = ly.conv2d(input,
256,
kernel_size=3,
strides=1,
name='g_conv2d_res_%s' % i)
cell = ly.batch_normal(cell, name='g_res_%s' % i)
cell = tf.nn.relu(cell)
input = cell
input = ly.deconv2d(input,
kernel_size=3,
strides=2,
name='g_deconv2d_0')
input = ly.batch_normal(input, name='g_bn_3')
input = tf.nn.relu(input)
input = ly.deconv2d(input,
kernel_size=3,
strides=2,
name='g_deconv2d_1')
input = ly.batch_normal(input, name='g_bn_4')
input = tf.nn.relu(input)
input = ly.conv2d(input,
3,
kernel_size=7,
strides=1,
name='g_conv2d_3')
input = ly.batch_normal(input, name='g_bn_5')
input = tf.nn.tanh(input)
input = tf.image.resize_images(input, (299, 299))
return input ## (-1,28,28,1)