Interface | Description |
---|---|
Block |
A
Block is a composable function that forms a neural network. |
SymbolBlock |
SymbolBlock is a Block is used to load models that were exported directly from
the engine in its native format. |
Class | Description |
---|---|
AbstractBlock |
AbstractBlock is an abstract implementation of Block . |
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.
|
LambdaBlock |
LambdaBlock is a Block with no parameters or children. |
ParallelBlock |
ParallelBlock is a Block 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. |
ParameterBlock |
ParameterBlock is an abstract implementation of Block . |
ParameterList |
Represents a set of names and Parameters.
|
SequentialBlock |
SequentialBlock is a Block whose children form a chain of blocks with each child
block feeding its output to the next. |
Enum | Description |
---|---|
ParameterType |
Enumerates the types of
Parameter . |
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:
ai.djl.nn.convolutional
ai.djl.nn.core
ai.djl.nn.norm
ai.djl.nn.pooling
ai.djl.nn.recurrent