niftynet.application.classification_application module

This module defines an image-level classification application that maps from images to scalar, multi-class labels.

This class is instantiated and initalized by the application_driver.

class ClassificationApplication(net_param, action_param, action)

Bases: niftynet.application.base_application.BaseApplication

This class defines an application for image-level classification problems mapping from images to scalar labels.

This is the application class to be instantiated by the driver and referred to in configuration files.

Although structurally similar to segmentation, this application supports different samplers/aggregators (because patch-based processing is not appropriate), and monitoring metrics.

REQUIRED_CONFIG_SECTION = 'CLASSIFICATION'

initialise_dataset_loader(data_param=None, task_param=None, data_partitioner=None)

initialise_resize_sampler()

initialise_aggregator()

initialise_sampler()

initialise_network()

add_confusion_matrix_summaries_(outputs_collector, net_out, data_dict)

This method defines several monitoring metrics that are derived from the confusion matrix

connect_data_and_network(outputs_collector=None, gradients_collector=None)

interpret_output(batch_output)

initialise_evaluator(eval_param)

add_inferred_output(data_param, task_param)