the DAEFormer is a U-Net like hierarchical pure transformer architecture.

The script train.py contains all the necessary steps for training the network. A list and dataloader for the Synapse dataset are also included. To load a network, use the --module argument when running the train script (--module <directory>.<module_name>.<class_name>, e.g. --module networks.DAEFormer.DAEFormer)

You can download the learned weights of the DAEFormer in the following table.

All implementation done by Rene Arimond. For any query please contact us for more information.

rene.arimond@lfb.rwth-aachen.de