def transition_up(self, x, scope, num_filters=None):
with tf.variable_scope(scope):
x = batch_norm(x, is_training=self.is_training_pl, scope='BN_1')
x = Relu(x)
x = conv_2d(x,
filter_size=1,
num_filters=int(x.get_shape().as_list()[-1] *
self.theta_up),
layer_name='conv',
add_reg=self.conf.use_reg,
add_batch_norm=self.conf.use_BN,
is_train=self.is_training_pl)
x = tf.nn.dropout(x, keep_prob=self.keep_prob_pl)
x = batch_norm(x, is_training=self.is_training_pl, scope='BN_2')
x = Relu(x)
if not num_filters:
num_filters = self.trans_out
x = deconv_2d(inputs=x,
filter_size=3,
num_filters=num_filters,
layer_name='deconv',
stride=2,
add_reg=self.conf.use_reg,
add_batch_norm=False,
is_train=self.is_training_pl)
x = tf.nn.dropout(x, keep_prob=self.keep_prob_pl)
return x
def up_conv(self, x):
num_out_channels = x.get_shape().as_list()[-1]
x = deconv_2d(inputs=x,
filter_size=3,
num_filters=num_out_channels,
layer_name='conv_up',
stride=2,
add_batch_norm=False,
is_train=self.is_training_pl)
return x
def up_conv(self, x):
num_out_channels = get_num_channels(x) // 2
x = deconv_2d(inputs=x,
filter_size=2,
num_filters=num_out_channels,
layer_name='conv_up',
stride=2,
add_batch_norm=self.conf.use_BN,
is_train=self.is_training_pl)
return x