dival.datasets.ellipses_dataset module
Provides EllipsesDataset.
- class dival.datasets.ellipses_dataset.EllipsesDataset(image_size=128, min_pt=None, max_pt=None, train_len=32000, validation_len=3200, test_len=3200, fixed_seeds=False)[source]
Bases:
GroundTruthDatasetDataset with images of multiple random ellipses.
This dataset uses
odl.phantom.ellipsoid_phantom()to create the images. The images are normalized to have a value range of[0., 1.]with a background value of0..- space
odl.uniform_discr(min_pt, max_pt, (image_size, image_size), dtype='float32'), with the parameters passed to__init__().
- shape
(image_size, image_size), with image_size parameter passed to__init__(). Default(128, 128).
- train_len
train_len parameter passed to
__init__(). Default32000.
- validation_len
validation_len parameter passed to
__init__(). Default3200.
- test_len
test_len parameter passed to
__init__(). Default3200.
- random_access
False
- num_elements_per_sample
1
- __init__(image_size=128, min_pt=None, max_pt=None, train_len=32000, validation_len=3200, test_len=3200, fixed_seeds=False)[source]
- Parameters:
image_size (int, optional) – Number of pixels per image dimension. Default:
128.min_pt ([int, int], optional) – Minimum values of the lp space. Default:
[-image_size/2, -image_size/2].max_pt ([int, int], optional) – Maximum values of the lp space. Default:
[image_size/2, image_size/2].train_len (int or None, optional) – Length of training set. Default:
32000. If None, infinitely many samples could be generated.validation_len (int, optional) – Length of training set. Default:
3200.test_len (int, optional) – Length of test set. Default:
3200.fixed_seeds (dict or bool, optional) – Seeds to use for random generation. The values of the keys
'train','validation'and'test'are used. If a seed is None or omitted, it is choosen randomly. IfTrueis passed, the seedsfixed_seeds={'train': 42, 'validation': 2, 'test': 1}are used. IfFalseis passed (the default), all seeds are chosen randomly.