The main module: the Network module

class nnfbp.Network.Network(nHiddenNodes, projector, trainData, valData, reductor=None, nTrain=1000000, nVal=1000000, tmpDir=None, createEmptyClass=False)

Bases: object

The neural network object that performs all training and reconstruction.

Parameters:

• nHiddenNodes (int) – The number of hidden nodes in the network.
• projector (A Projector object (see, for example: nnfbp.SimpleCPUProjector)) – The projector to use.
• trainData (A DataSet object (see: nnfbp.DataSet)) – The training data set.
• valData (A DataSet object (see: nnfbp.DataSet)) – The validation data set.
• reductor (A Reductor object (see: nnfbp.Reductors, default:LogSymReductor)) – Optional reductor to use.
• nTrain (int) – Number of pixels to pick out of training set.
• nVal (int) – Number of pixels to pick out of validation set.
• tmpDir (string) – Optional temporary directory to use.
• createEmptyClass (boolean) – Used internally when loading from disk, to create an empty object. Do not use directly.

reconstruct(sinogram)

Reconstruct an image from a sinogram, after training.

Parameters:sinogram (numpy.ndarray) – The sinogram to reconstruct.

saveToDisk(fn)

Save a trained network to disk, so that it can be used later without retraining.

Parameters:fn (string) – Filename to save it to.

train()

Train the network using the Levenberg-Marquardt method.

nnfbp.Network.readFromDisk(fn, projector)

Read a saved network from disk. The specified projector should be similar to the one used during training.

Parameters:

• fn (string) – Filename to load network from.
• projector (A Projector object (see, for example: nnfbp.SimpleCPUProjector)) – Projector to use when reconstructing.

Returns:

A nnfbp.Network.Network instance, ready to reconstruct with.