ndsampler.abstract_sampler module¶

class ndsampler.abstract_sampler.AbstractSampler[source]¶

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¶

lookup_class_name(class_id)[source]¶

lookup_class_id(class_name)[source]¶

load_sample(tr, pad=None, window_dims=None, visible_thresh=0.1)[source]¶

property n_positives¶

load_item(index, pad=None, window_dims=None)[source]¶

load_positive(index=None, pad=None, window_dims=None, rng=None)[source]¶

load_negative(index=None, pad=None, window_dims=None, rng=None)[source]¶

load_image(image_id)[source]¶

image_ids()[source]¶

preselect(**kwargs)[source]¶: Setup a pool of training examples before the epoch begins