niftynet.application.base_application module

class niftynet.application.base_application.BaseApplication

Bases: object

BaseApplication represents an interface. Each application type_str should support to use the standard training and inference driver

REQUIRED_CONFIG_SECTION = None

check_initialisations()

connect_data_and_network(outputs_collector=None, gradients_collector=None)

get_sampler()

gradient_op = None

initialise_dataset_loader(data_param=None, task_param=None)

initialise_network()

This function create an instance of network sets self.net :return: None

initialise_sampler()

set samplers take self.reader as input and generates sequences of ImageWindow that will be fed to the networks This function sets self.sampler

interpret_output(batch_output)

implement output interpretations, e.g., save to hard drive cache output windows :param batch_output: outputs by running the tf graph :return: True indicates the driver should continue the loop

False indicates the drive should stop

is_training = True

net = None

optimiser = None

output_decoder = None

reader = None

sampler = None

set_network_update_op(gradients)

stop()

training_ops(start_iter=0, end_iter=1)

Specify the network update operation at each iteration app can override this updating method if necessary

class niftynet.application.base_application.SingletonApplication

Bases: type