Package ai.djl.nn
Contains classes to construct neural networks.
The primary construct used to build up the networks is the Block
(see for
details). This package contains a number of implementations of blocks as well as helpers for
blocks.
The following subpackages also contain a number of standard neural network operations to use with blocks:
-
Interface Summary Interface Description Block ABlock
is a composable function that forms a neural network.BlockFactory Block factory is a component to make standard for block creating and saving procedure.SymbolBlock SymbolBlock
is aBlock
is used to load models that were exported directly from the engine in its native format. -
Class Summary Class Description AbstractBaseBlock This provides shared functionality for both the DJL-basedAbstractBlock
s and the importedAbstractSymbolBlock
s.AbstractBlock AbstractBlock
is an abstract implementation ofBlock
.AbstractSymbolBlock AbstractSymbolBlock
is an abstract implementation ofSymbolBlock
.Activation Utility class that provides activation functions and blocks.BlockList Represents a set of names and Blocks.Blocks Utility class that provides some useful blocks.IdentityBlockFactory ABlockFactory
class that creates IdentityBlock.LambdaBlock LambdaBlock
is aBlock
with no parameters or children.ParallelBlock ParallelBlock
is aBlock
whose children form a parallel branch in the network and are combined to produce a single output.Parameter Parameter
is a container class that holds a learnable parameter of a model.Parameter.Builder A Builder to construct aParameter
.ParameterList Represents a set of names and Parameters.SequentialBlock SequentialBlock
is aBlock
whose children form a chain of blocks with each child block feeding its output to the next. -
Enum Summary Enum Description Parameter.Type Enumerates the types ofParameter
. -
Exception Summary Exception Description UninitializedParameterException Thrown to indicate that aParameter
was not initialized.