DeepCL
v4.0.0rc5
Deep convolutional neural networks using OpenCL
|
Batcher | Runs an epoch for a single set of already-loaded data |
ConvolutionalMaker | Use to create a convolutional layer |
FullyConnectedMaker | Use to create a fully-connected layer |
GenericLoader | Use to load data from file, given the path to the images file |
InputLayerMaker | Use to create an InputLayer, which can be added to a NeuralNet |
Layer | A single layer within the neural net |
NetdefToNet | Add layers to a NeuralNet object, based on a netdef-string |
NetLearner | Runs multiple learning epochs using Batcher objects |
NetLearnerOnDemand | Learns multiple epochs, for data that wont fit in memory |
NeuralNet | NeuralNet: main container class for network layers |
NormalizationLayerMaker | Use to add a NormalizationLayer to a NeuralNet |
OnDemandBatcher | Learns an entire epoch of training, for data that wont fit in memory |
PoolingMaker | Use to create a Max-Pooling layer |
RandomPatchesMaker | Use to create a RandomPatches Layer |
RandomTranslationsMaker | Use to create a RandomTranslations Layer |
WeightsPersister | Use to read/write weights from a NeuralNet |