Neural network layers, which are main building blocks of a neural network. Neural network consists of a sequence of layers.
Interface Summary Interface Description LayerCommon base interface for all types of neural network layers.
Class Summary Class Description AbstractLayerBase class for different types of layers. ConvolutionalLayerConvolutional layer performs image convolution operation on outputs of a previous layer using filters. Filter Filters FlattenLayerJust transform outputs from prev 3d layer into flat 1d tensor in formward pass backward pass will be same as backward for fc, and for 3d layers backwardFromFc Automaticly add after 2d or 3d layer to transition to fc layers. FullyConnectedLayerFully connected layer is used as hidden layer in the neural network, and it has a single row of units/nodes/neurons connected to all neurons in previous and next layer. FullyConnectedLayer1Fully connected layer is used as hidden layer in the neural network, and it has a single row of units/nodes/neurons connected to all neurons in previous and next layer. InputLayerInput layer in neural network, which accepts external input, and sends it to next layer in a network. MaxPoolingLayerThis layer performs max pooling operation in convolutional neural network, which scales down output from previous layer by taking max outputs from small predefined filter areas. OutputLayerOutput layer of a neural network, which gives the final output of a network. SoftmaxOutputLayerOutput layer with softmax activation function.
Enum Summary Enum Description LayerTypeEnum for supported types of layers.