def dense_residual_block(self, model_layer, name):
with tf.name_scope('dense_residual_block') as scope:
last_layer = self.last_layer
if 'function' in model_layer:
activation = model_layer['function']
else:
activation = 'relu'
# original residual unit
shape = self.network[last_layer].get_output_shape()
num_units = shape[-1].value
self.network[name+'_1resid'] = layers.DenseLayer(self.network[last_layer], num_units=num_units, b=None, **self.seed)
self.network[name+'_1resid_norm'] = layers.BatchNormLayer(self.network[name+'_1resid'], self.placeholders['is_training'])
self.network[name+'_1resid_active'] = layers.ActivationLayer(self.network[name+'_1resid_norm'], function=activation)
if 'dropout_block' in model_layer:
placeholder_name = 'keep_prob_'+str(self.num_dropout)
self.placeholders[placeholder_name] = tf.placeholder(tf.float32, name=placeholder_name)
self.feed_dict[placeholder_name] = 1-model_layer['dropout_block']
self.num_dropout += 1
self.network[name+'_dropout1'] = layers.DropoutLayer(self.network[name+'_1resid_active'], keep_prob=self.placeholders[placeholder_name])
lastname = name+'_dropout1'
else:
lastname = name+'_1resid_active'
self.network[name+'_2resid'] = layers.DenseLayer(self.network[lastname], num_units=num_units, b=None, **self.seed)
self.network[name+'_2resid_norm'] = layers.BatchNormLayer(self.network[name+'_2resid'], self.placeholders['is_training'])
self.network[name+'_resid_sum'] = layers.ElementwiseSumLayer([self.network[last_layer], self.network[name+'_2resid_norm']])
self.network[name+'_resid'] = layers.ActivationLayer(self.network[name+'_resid_sum'], function=activation)
self.last_layer = name+'_resid'
def conv2d_residual_block(self, model_layer, name):
last_layer = self.last_layer
filter_size = model_layer['filter_size']
if 'function' in model_layer:
activation = model_layer['function']
else:
activation = 'relu'
# original residual unit
shape = self.network[last_layer].get_output_shape()
num_filters = shape[-1].value
if not isinstance(filter_size, (list, tuple)):
filter_size = (filter_size, filter_size)
if 'W' not in model_layer.keys():
W = init.GlorotUniform(**self.seed)
else:
W = model_layer['W']
self.network[name + '_1resid'] = layers.Conv2DLayer(
self.network[last_layer],
num_filters=num_filters,
filter_size=filter_size,
W=W,
padding='SAME')
self.network[name + '_1resid_norm'] = layers.BatchNormLayer(
self.network[name + '_1resid'], self.placeholders['is_training'])
self.network[name + '_1resid_active'] = layers.ActivationLayer(
self.network[name + '_1resid_norm'], function=activation)
if 'dropout_block' in model_layer:
placeholder_name = 'keep_prob_' + str(self.num_dropout)
self.placeholders[placeholder_name] = tf.placeholder(
tf.float32, name=placeholder_name)
self.feed_dict[placeholder_name] = 1 - model_layer['dropout_block']
self.num_dropout += 1
self.network[name + '_dropout1'] = layers.DropoutLayer(
self.network[name + '_1resid_active'],
keep_prob=self.placeholders[placeholder_name])
lastname = name + '_dropout1'
else:
lastname = name + '_1resid_active'
self.network[name + '_2resid'] = layers.Conv2DLayer(
self.network[lastname],
num_filters=num_filters,
filter_size=filter_size,
W=W,
padding='SAME')
self.network[name + '_2resid_norm'] = layers.BatchNormLayer(
self.network[name + '_2resid'], self.placeholders['is_training'])
self.network[name + '_resid_sum'] = layers.ElementwiseSumLayer(
[self.network[last_layer], self.network[name + '_2resid_norm']])
self.network[name + '_resid'] = layers.ActivationLayer(
self.network[name + '_resid_sum'], function=activation)
self.last_layer = name + '_resid'