ndsampler.abstract_sampler

Module Contents

Classes

AbstractSampler

API for Samplers, not all methods need to be implemented depending on the

class ndsampler.abstract_sampler.AbstractSampler

Bases: object

API for Samplers, not all methods need to be implemented depending on the use case (for example, load_sample may not be defined if positive / negative cases are generated on the fly).

property class_ids(self)
abstract lookup_class_name(self, class_id)
abstract lookup_class_id(self, class_name)
abstract load_sample(self, tr, pad=None, window_dims=None, visible_thresh=0.1)
property n_positives(self)
abstract load_item(self, index, pad=None, window_dims=None)
abstract load_positive(self, index=None, pad=None, window_dims=None, rng=None)
abstract load_negative(self, index=None, pad=None, window_dims=None, rng=None)
abstract load_image(self, image_id)
abstract image_ids(self)
abstract preselect(self, **kwargs)

Setup a pool of training examples before the epoch begins