Uses of Record Class
ai.beestream.jitnn.SparseMatrix.Valued
Packages that use SparseMatrix.Valued
Package
Description
The jitNN API:
Tensor (n-dimensional arrays, lazy on TornadoVM
devices), reverse-mode differentiation (Tensor.backward(), Grad),
the functional operators of F, linear algebra (Linalg),
Fourier transforms (Fft), sparse matrices (SparseMatrix),
mixed precision (Autocast) and user-defined operators
(CustomOp).Neural-network modules after PyTorch's
torch.nn: Module and
Sequential, linear and convolution layers, pooling, normalisation,
attention, embeddings, recurrent layers (LSTM, GRU), graph convolution, activations, and data-parallel
training (DataParallel).-
Uses of SparseMatrix.Valued in ai.beestream.jitnn
Methods in ai.beestream.jitnn that return SparseMatrix.ValuedModifier and TypeMethodDescriptionstatic SparseMatrix.ValuedSparseMatrix.gcn(int n, int[] src, int[] dst) The normalised adjacency of a graph convolutional network (Kipf and Welling, 2017), D^-1/2 (A + I) D^-1/2 for the directed edges src[e] -> dst[e] of an n-node graph (messages flow from source to destination, as in PyTorch Geometric's GCNConv). -
Uses of SparseMatrix.Valued in ai.beestream.jitnn.nn
Methods in ai.beestream.jitnn.nn with parameters of type SparseMatrix.ValuedModifier and TypeMethodDescriptionGraphConv.forward(Tensor x, SparseMatrix.Valued adjacency) Applies the layer to node features x [nodes, in] over the graph's normalised adjacency (seeSparseMatrix.gcn(int, int[], int[])).GraphConv.graph(SparseMatrix.Valued adjacency) Sets the graph the next forward calls use.