QMRITools`
QMRITools`
TrainSegmentationNetwork
TrainSegmentationNetwork[{inFol,outFol}]
trains a segmentation network. The correctly prepared training data should be stored in inFol. The progress each round will be saved in outFol.
TrainSegmentationNetwork[{inFol,outFol},netCont]
does the same but defines how to continue with netCont. If netCont is "Start" training will be restarted. If netCont is a initialized network or network file (wlnet) this will be used. If netCont is a a outFol the last saved network will be used.
Details
- The following options can be given:
-
PatchSize {32, 96, 96} PatchSize is an option for TrainSegmentationNetwork. Defines the patch size used in the network training. DownsampleSchedule {{1, 2, 2}, {2, 2, 2}, {1, 2, 2}, {2, 2, 2}} DownsampleSchedule is an option for MakeUnet. It defines how the data is downsampled for each of the deeper layers of the Unet. By default is is a factor two for each layer. A custum schedual for a 4 layer 3D Unet could be {{2,2,2},{1,2,2},{2,2,2},{1,2,2}}. NetworkDepth 5 NetworkDepth is an option for MakeUnet. It specifief how deep the UNET will be. InputFilters 24 InputFilters is an option for MakeUnet. It defines the amount of convolutional filters of the the first UNET block. DropoutRate 0.2 DropoutRate is an option for MakeUnet. It specifies how musch dropout is used after each block. It is a value between 0 and 1, default is .2. BlockType "ResNet" BlockType is an option for MakeUnet. It specifies which block are used to build the network. Values can be "UNET", "ResNet", "UResNet", "DenseNet" or "UDenseNet". BatchSize 4 BatchSize is an option for NetTrain and related functions that specifies the size of a batch of examples to process together. RoundLength 256 RoundLength is an option for TrainSegmentationNetwork. Defines how many batches will be seen during eacht training round. MaxTrainingRounds 500 MaxTrainingRounds is an option for NetTrain and related functions that specifies the maximum number of rounds of training to do. AugmentData True AugmentData is an option for GetTrainData and TrainSegmentationNetwork. If set True the trainingdata is augmented.