Return result as numpy array (labels x metrics).

Converts a tuple or a list to the correct `data_format`. It does so by switching the positions of its elements. # Arguments shape: Tup

If self.all_val_eval_metrics is unused (len=0) then we fall back to using -self.all_val_losses for the MA to determine early stopping

disable nnunet postprocessing. this would just waste computation time and does not benefit brats !!!We run this with use_sliding_win

This should run after cropping :param folder: :return:

folder needs the imagesTr, imagesTs and labelsTr subfolders. There also needs to be a dataset.json checks if all training cases and labels ar

Implementation of FPN head for segmentation models according to: http://presentations.cocodataset.org/COCO17-Stuff-FAIR.pdf Args:

Instantiates the Inception-ResNet v2 architecture. Optionally loads weights pre-trained on ImageNet. Note that when using TensorFlow, for best

Instantiates the Inception v3 architecture. Optionally loads weights pre-trained on ImageNet. Note that when using TensorFlow, for best pe

Version of Linkent model (https://arxiv.org/pdf/1707.03718.pdf) This implementation by default has 4 skip connection links (original - 3).

Exploit the capability of global context information by different-regionbased context aggregation through pyramid pooling module together wit

:param folder_with_cropped_data: :param overwrite: If True then precomputed values will not be used and instead recomputed from the d

:param normalization_scheme_per_modality: dict {0:'nonCT'} :param use_nonzero_mask: {0:False} :param intensityproperties:

This one finds a mask of nonzero elements (must be nonzero in all modalities) and crops the image to that mask. In the case of BRaTS

This is the basic data loader for 2D networks. It uses preprocessed data as produced by my (Fabian) preprocessing. You can load the d

A generic class that can train almost any neural network (RNNs excluded). It provides basic functionality such as the training loop,

:param deterministic: :param fold: can be either [0 ... 5) for cross-validation, 'all' to train on all available training data or