def _create(self):
base_model = KerasResNet50(include_top=False,
input_tensor=self.get_input_tensor())
self.make_net_layers_non_trainable(base_model)
x = base_model.output
x = Dropout(self.dropout)(x)
x = Flatten()(x)
# we could achieve almost the same accuracy without this layer, buy this one helps later
# for novelty detection part and brings much more useful features.
#x = Dense(self.noveltyDetectionLayerSize, activation='elu', name=self.noveltyDetectionLayerName)(x)
#x = Dropout(0.5)(x)
if self.run_config.main.classification_type == _config.CLASSIFICATION_TYPE.CLASSIFICATION:
predictions = Dense(self.run_config.data.nb_classes,
activation='softmax',
name='predictions')(x)
elif self.run_config.main.classification_type == _config.CLASSIFICATION_TYPE.REGRESSION:
predictions = Dense(1, activation='linear', name='regression')(x)
elif self.run_config.main.classification_type == _config.CLASSIFICATION_TYPE.MULTIPLE_REGRESSION:
predictions = Dense(self.run_config.data.nb_classes,
activation='linear',
name='multiple_regression')(x)
else:
raise ValueError("Error, unknown classification_type: <%s>" %
self.run_config.main.classification_type)
self.model = Model(input=base_model.input, output=predictions)
def _create(self):
base_model = KerasResNet50(include_top=False, input_tensor=self.get_input_tensor())#create base_model
self.make_net_layers_non_trainable(base_model)#make net layers non trainable
x = base_model.output
x = Flatten()(x)
x = Dropout(0.5)(x)
# we could achieve almost the same accuracy without this layer, buy this one helps later
# for novelty detection part and brings much more useful features.
x = Dense(self.noveltyDetectionLayerSize, activation='elu', name=self.noveltyDetectionLayerName)(x)
x = Dropout(0.5)(x)
predictions = Dense(len(config.classes), activation='softmax', name='predictions')(x)
self.model = Model(input=base_model.input, output=predictions)
def _create(self):
base_model = KerasResNet50(include_top=False,
input_tensor=self.get_input_tensor())
self.make_net_layers_non_trainable(base_model)
x = base_model.output
x = Flatten()(x)
x = Dropout(0.5)(x)
x = Dense(128, activation='elu',
name=self.noveltyDetectionLayerName)(x)
x = Dense(128, activation='elu',
name=self.noveltyDetectionLayerName1)(x)
x = Dropout(0.5)(x)
predictions = Dense(len(config.classes),
activation='softmax',
name='predictions')(x)
self.model = Model(input=base_model.input, output=predictions)
self.model.summary()
def define(self, optimizer=Adam(lr=config.configured_learning_rate)):
self.optimizer = optimizer
keras_model = KerasResNet50(weights=None,
include_top=True,
input_tensor=self.get_input_tensor(),
input_shape=self.get_input_shape(),
classes=len(config.configured_classes))
self.make_net_layers_non_trainable(keras_model)
#use standard model or fine turn model
if config.use_fineturn_model:
self.model = self.fineturn(self, keras_model)
else:
self.model = Model(
input=keras_model.input,
output=keras_model.output) #this means NO CHANGE