Class EmbeddingBag
java.lang.Object
ai.beestream.jitnn.nn.Module
ai.beestream.jitnn.nn.EmbeddingBag
- All Implemented Interfaces:
AutoCloseable
EmbeddingBag: bags of INT32 indices (one flat list plus bag offsets) to the sum, mean or max of
their embedding rows, PyTorch's nn.EmbeddingBag with standard normal initial weights.
-
Constructor Summary
ConstructorsConstructorDescriptionEmbeddingBag(int count, int dim, F.BagMode mode, long seed) A table ofcountvectors of sizedim, standard normal fromseed, whose bags combine asmodesays. -
Method Summary
Methods inherited from class Module
buffer, buffers, child, close, isClosed, isTraining, loadStateDict, parameter, parameterCount, parameters, stateDict, train, zeroGrad
-
Constructor Details
-
EmbeddingBag
A table ofcountvectors of sizedim, standard normal fromseed, whose bags combine asmodesays.
-
-
Method Details
-
weight
The table [count, dim]. -
forward
-
forward
-