Flexible federated learning enables institutions to jointly train deep learning models even when data is non-uniformly labeled. The resulting models are superior to models which are trained with co…

Provides everything needed for high performance data loading and augmentation in pytorch.

A baseline repository to train a unet with delira

Tensorflow Code for "PHiSeg: Capturing Uncertainty in Medical Image Segmentation", Proc. MICCAI 2019

A U-Net combined with a variational auto-encoder that is able to learn conditional distributions over semantic segmentations.

A framework for data augmentation for 2D and 3D image classification and segmentation

Lightweight framework for fast prototyping and training deep neural networks with PyTorch and TensorFlow