def init(model_path, is_decaf6=False):
if is_decaf6:
K.set_image_data_format('channels_first')
base_model = decaf()
predictions = Dense(25, activation='softmax')(base_model.output)
model = Model(inputs=base_model.input, outputs=predictions)
model.load_weights(model_path, by_name=True)
else:
model = load_model(model_path)
model.compile(optimizer='rmsprop', loss='categorical_crossentropy',
metrics=['accuracy', metrics.top_k_categorical_accuracy])
return model
params = vars(args)
# BUILDING MODEL
if model_name == 'alexnet_empty':
K.set_image_data_format('channels_first')
size = (227, 227)
model = alexnet(weights=None)
for layer in model.layers:
layer.trainable = True
elif model_name == 'decaf6':
K.set_image_data_format('channels_first')
size = (227, 227)
base_model = decaf()
predictions = Dense(25, activation='softmax')(base_model.output)
model = Model(inputs=base_model.input, outputs=predictions)
for layer in base_model.layers:
layer.trainable = False
elif model_name == 'resnet':
K.set_image_data_format('channels_last')
size = (224, 224)
base_model = resnet_trained(n_layers_trainable)
predictions = Dense(25, activation='softmax')(base_model.output)
model = Model(inputs=base_model.input, outputs=predictions)
elif model_name == 'inception':
K.set_image_data_format('channels_last')