Uses of Package
deepnetts.net.layers
Packages that use deepnetts.net.layers
Package
Description
Neural network architectures with their corresponding builders.
Neural network layers, which are main building blocks of a neural network.
Optimization methods used by training algorithm.
-
Classes in deepnetts.net.layers used by deepnetts.accl.spiClassDescriptionConvolutional layer performs image convolution operation on outputs of a previous layer using filters.Transforms outputs from previous 3D layer into a flatten 1D tensor in forward pass, Backward pass propagates weighted errors/deltas from the next fully connected layer.Fully connected layer is used as a hidden layer in a neural network, and it has a single row of units/nodes/neurons connected to all neurons in previous and next layer.This 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.Output layer of a neural network.Output layer with softmax activation function.
-
Classes in deepnetts.net.layers used by deepnetts.netClassDescriptionBase class for different types of layers.Settings of a convolutional filter which is used to learn to detect pixel patterns.Input layer in a neural network.Output layer of a neural network.
-
Classes in deepnetts.net.layers used by deepnetts.net.layersClassDescriptionBase class for different types of layers.Settings of a convolutional filter which is used to learn to detect pixel patterns.Common base interface for all types of neural network layers.Supported types of layers.Output layer of a neural network.
-
Classes in deepnetts.net.layers used by deepnetts.net.train.opt