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