A PyTorch-based library for working with 3D and 2D convolutional neural networks, with focus on semantic segmentation of volumetric biomedical image data
just as inspiration
this is obviously not ok as default
the ignore class id(s) should somehow end up in that function but e3 currently doesn’t know about them (the class_weights) at all
just as inspiration this is obviously not ok as default the ignore class id(s) should somehow end up in that function but e3 currently doesn’t know about them (the class_weights) at all