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
def down_conv(self, x):
num_out_channels = get_num_channels(x) * 2
x = conv_2d(inputs=x,
filter_size=2,
num_filters=num_out_channels,
layer_name='conv_down',
stride=2,
add_batch_norm=self.conf.use_BN,
is_train=self.is_training_pl,
keep_prob=self.keep_prob_pl,
activation=self.act_fcn)
return x
def down_conv(self, x):
num_out_channels = get_num_channels(x)
x = BN_Relu_conv_2d(inputs=x,
filter_size=1,
num_filters=num_out_channels,
layer_name='conv_down',
stride=1,
add_batch_norm=self.conf.use_BN,
is_train=self.is_training_pl,
use_relu=True)
x = tf.nn.dropout(x, self.keep_prob_pl)
x = max_pool(x, self.conf.pool_filter_size, stride=2, name='maxpool')
return x
def conv_block_up(self, layer_input, fine_grained_features,
num_convolutions):
x = tf.concat((layer_input, fine_grained_features), axis=-1)
n_channels = get_num_channels(layer_input)
for i in range(num_convolutions):
x = conv_2d(inputs=x,
filter_size=self.k_size,
num_filters=n_channels,
layer_name='conv_' + str(i + 1),
add_batch_norm=self.conf.use_BN,
is_train=self.is_training_pl,
keep_prob=self.keep_prob_pl,
dropconnect=True)
if i == num_convolutions - 1:
x = x + layer_input
x = self.act_fcn(x, name='prelu_' + str(i + 1))
return x
def conv_block_down(self, layer_input, num_convolutions):
x = layer_input
n_channels = get_num_channels(x)
if n_channels == 1:
n_channels = self.conf.start_channel_num
for i in range(num_convolutions):
x = conv_2d(inputs=x,
filter_size=self.k_size,
num_filters=n_channels,
layer_name='conv_' + str(i + 1),
add_batch_norm=self.conf.use_BN,
is_train=self.is_training_pl,
keep_prob=self.keep_prob_pl,
dropconnect=True)
if i == num_convolutions - 1:
x = x + layer_input
x = self.act_fcn(x, name='prelu_' + str(i + 1))
return x