Uses of Enum Class
ai.beestream.jitnn.F.BagMode
Packages that use F.BagMode
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 F.BagMode in ai.beestream.jitnn
Subclasses with type arguments of type F.BagMode in ai.beestream.jitnnModifier and TypeClassDescriptionstatic enumHowF.embeddingBag(Tensor, int[], Tensor, F.BagMode)andF.segmentReduce(Tensor, int[], F.BagMode)combine the rows of a bag.Methods in ai.beestream.jitnn that return F.BagModeModifier and TypeMethodDescriptionstatic F.BagModeReturns the enum constant of this class with the specified name.static F.BagMode[]F.BagMode.values()Returns an array containing the constants of this enum class, in the order they are declared.Methods in ai.beestream.jitnn with parameters of type F.BagModeModifier and TypeMethodDescriptionstatic TensorF.embeddingBag(Tensor indices, int[] offsets, Tensor weight, F.BagMode mode) EmbeddingBag (PyTorch's, 1-D input with offsets): the rows ofweightpicked by the INT32indices, combined per bag bymode.static TensorF.segmentReduce(Tensor x, int[] offsets, F.BagMode mode) Sum, mean or max of the row segments of x [rows, D]: segment b covers rows offsets[b] .. offsets[b + 1] - 1, the last to the end; an empty segment gives zeros. -
Uses of F.BagMode in ai.beestream.jitnn.nn
Constructors in ai.beestream.jitnn.nn with parameters of type F.BagModeModifierConstructorDescriptionEmbeddingBag(int count, int dim, F.BagMode mode, long seed) A table ofcountvectors of sizedim, standard normal fromseed, whose bags combine asmodesays.