A PyTorch-based library for working with 3D and 2D convolutional neural networks, with focus on semantic segmentation of volumetric biomedical image data
Both the data loading (PatchCreator etc.) and the training components (StoppableTrainer) currently only support 3D (volumetric) image data sets. Support for 2D images would be nice, as long as it doesn't interfere with 3D support. In many parts of the code, 2D support could be transparently added as a special case of 3D without code duplication.
Basic support for 2D images and an example data set for 2D training are available since #22. There are currently no plans for better built-in 2D data loading features, but contributions in this regard are welcome.
Both the data loading (
PatchCreator
etc.) and the training components (StoppableTrainer
) currently only support 3D (volumetric) image data sets. Support for 2D images would be nice, as long as it doesn't interfere with 3D support. In many parts of the code, 2D support could be transparently added as a special case of 3D without code duplication.