def bottleneck_block(self, x, scope):
with tf.variable_scope(scope):
x = batch_norm(x, is_training=self.is_training, scope='BN1')
x = Relu(x)
x = conv_3d(x, filter_size=1, num_filters=4 * self.k, layer_name='conv1', add_reg=self.conf.use_reg)
x = drop_out(x, keep_prob=self.keep_prob)
x = batch_norm(x, is_training=self.is_training, scope='BN2')
x = Relu(x)
x = conv_3d(x, filter_size=3, num_filters=self.k, layer_name='conv2', add_reg=self.conf.use_reg)
x = drop_out(x, keep_prob=self.keep_prob)
return x
def transition_down(self, x, scope):
with tf.variable_scope(scope):
x = batch_norm(x, is_training=self.is_training, scope='BN')
x = Relu(x)
x = conv_3d(x, filter_size=1, num_filters=self.trans_out, layer_name='conv', add_reg=self.conf.use_reg)
x = drop_out(x, keep_prob=self.keep_prob)
x = avg_pool(x, ksize=2, stride=2, scope='avg_pool')
return x
def transition_up(self, x, scope, num_filters=None):
with tf.variable_scope(scope):
x = batch_norm(x, is_training=self.is_training, scope='BN')
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)
x = drop_out(x, keep_prob=self.keep_prob)
x = batch_norm(x, is_training=self.is_training, scope='BN')
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,
batch_norm=False,
is_train=self.is_training)
x = drop_out(x, keep_prob=self.keep_prob)
return x
def transition_up(self, x, out_shape, scope, num_filters=None):
with tf.variable_scope(scope):
x = batch_norm(x, is_training=self.is_training, scope='BN')
x = Relu(x)
if not num_filters:
num_filters = self.trans_out
x = deconv_3d(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,
out_shape=out_shape)
x = drop_out(x, keep_prob=self.keep_prob)
return x