HealthML / active-segmentation

ActiveSegmentation: A Simulation Framework for Benchmarking Active Learning Strategies for 3D Medical Image Segmentation
GNU Affero General Public License v3.0
16 stars 1 forks source link

Adapt random sampling strategy to perform fully random sampling #98

Closed josafatburmeister closed 2 years ago

josafatburmeister commented 2 years ago

Currently, the random sampling strategy randomly samples slices from one scan and starts to sample from the next scan only when all slices from the previous scan were sampled. This PR adapts the random sampling strategy to perform fully random sampling instead.