Package ai.djl.nn.core
Class LinearCollection
- java.lang.Object
-
- ai.djl.nn.AbstractBaseBlock
-
- ai.djl.nn.AbstractBlock
-
- ai.djl.nn.core.LinearCollection
-
- All Implemented Interfaces:
Block
public class LinearCollection extends AbstractBlock
A LinearCollection block applies \(m\) linear transformations \(Y_i = X_i W_i + b_i\) for each \(i \in [1, \ldots, m]\) and \(m = \prod_{j=1}^t s_j\). \(t\) is typically 1, so compared to aLinear
block, the involved shapes have typically one split dimension added which separates the different linear transformations from each other. Another difference to aLinear
block is that the weight is not transposed (to align with the internally used algebraic operationNDArray.matMul(NDArray)
).It has the following shapes:
- input X: [x_1, s_1, s_2, …, s_t, input_dim]
- weight W: [s_1, s_2, …, s_t, input_dim, units]
- Bias b: [s_1, s_2, …, s_t, units]
- output Y: [x_1, s_1, s_2, …, s_t, units]
The LinearCollection block should be constructed using
LinearCollection.Builder
.
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description static class
LinearCollection.Builder
The Builder to construct aLinearCollection
type ofBlock
.
-
Field Summary
-
Fields inherited from class ai.djl.nn.AbstractBlock
children, parameters
-
Fields inherited from class ai.djl.nn.AbstractBaseBlock
inputNames, inputShapes, outputDataTypes, version
-
-
Method Summary
All Methods Static Methods Instance Methods Concrete Methods Modifier and Type Method Description protected void
beforeInitialize(Shape... inputShapes)
Performs any action necessary before initialization.static LinearCollection.Builder
builder()
Creates a builder to build aLinear
.ai.djl.util.PairList<java.lang.String,Shape>
describeInput()
Returns aPairList
of input names, and shapes.protected NDList
forwardInternal(ParameterStore parameterStore, NDList inputs, boolean training, ai.djl.util.PairList<java.lang.String,java.lang.Object> params)
A helper forBlock.forward(ParameterStore, NDList, boolean, PairList)
after initialization.Shape[]
getOutputShapes(Shape[] inputs)
Returns the expected output shapes of the block for the specified input shapes.NDList
linear(NDArray input, NDArray weight, NDArray bias)
Applies linear transformations to the incoming data.void
loadMetadata(byte loadVersion, java.io.DataInputStream is)
Overwrite this to load additional metadata with the parameter values.void
prepare(Shape[] inputShapes)
Sets the shape ofParameter
s.protected void
saveMetadata(java.io.DataOutputStream os)
Override this method to save additional data apart from parameter values.-
Methods inherited from class ai.djl.nn.AbstractBlock
addChildBlock, addChildBlock, addChildBlockSingleton, addParameter, getChildren, getDirectParameters
-
Methods inherited from class ai.djl.nn.AbstractBaseBlock
cast, clear, forward, forward, forwardInternal, getInputShapes, getOutputDataTypes, getParameters, initialize, initializeChildBlocks, isInitialized, loadParameters, readInputShapes, saveInputShapes, saveParameters, setInitializer, setInitializer, setInitializer, toString
-
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
-
Methods inherited from interface ai.djl.nn.Block
forward, freezeParameters, getOutputShapes
-
-
-
-
Method Detail
-
forwardInternal
protected NDList forwardInternal(ParameterStore parameterStore, NDList inputs, boolean training, ai.djl.util.PairList<java.lang.String,java.lang.Object> params)
A helper forBlock.forward(ParameterStore, NDList, boolean, PairList)
after initialization.- Specified by:
forwardInternal
in classAbstractBaseBlock
- Parameters:
parameterStore
- the parameter storeinputs
- the input NDListtraining
- true for a training forward passparams
- optional parameters- Returns:
- the output of the forward pass
-
getOutputShapes
public Shape[] getOutputShapes(Shape[] inputs)
Returns the expected output shapes of the block for the specified input shapes.- Parameters:
inputs
- the shapes of the inputs- Returns:
- the expected output shapes of the block
-
describeInput
public ai.djl.util.PairList<java.lang.String,Shape> describeInput()
Returns aPairList
of input names, and shapes.- Specified by:
describeInput
in interfaceBlock
- Overrides:
describeInput
in classAbstractBaseBlock
- Returns:
- the
PairList
of input names, and shapes
-
beforeInitialize
protected void beforeInitialize(Shape... inputShapes)
Performs any action necessary before initialization. For example, keep the input information or verify the layout.- Overrides:
beforeInitialize
in classAbstractBaseBlock
- Parameters:
inputShapes
- the expected shapes of the input
-
prepare
public void prepare(Shape[] inputShapes)
Sets the shape ofParameter
s.- Overrides:
prepare
in classAbstractBaseBlock
- Parameters:
inputShapes
- the shapes of inputs
-
saveMetadata
protected void saveMetadata(java.io.DataOutputStream os) throws java.io.IOException
Override this method to save additional data apart from parameter values.This default implementation saves the currently set input shapes.
- Overrides:
saveMetadata
in classAbstractBaseBlock
- Parameters:
os
- the non-null output stream the parameter values and metadata are written to- Throws:
java.io.IOException
- saving failed
-
loadMetadata
public void loadMetadata(byte loadVersion, java.io.DataInputStream is) throws java.io.IOException, MalformedModelException
Overwrite this to load additional metadata with the parameter values.If you overwrite
AbstractBaseBlock.saveMetadata(DataOutputStream)
or need to provide backward compatibility to older binary formats, you probably need to overwrite this. This default implementation checks if the version number fits, if not it throws anMalformedModelException
. After that it restores the input shapes.- Overrides:
loadMetadata
in classAbstractBaseBlock
- Parameters:
loadVersion
- the version used for loading this metadata.is
- the input stream we are loading from- Throws:
java.io.IOException
- loading failedMalformedModelException
- data can be loaded but has wrong format
-
linear
public NDList linear(NDArray input, NDArray weight, NDArray bias)
Applies linear transformations to the incoming data.- Parameters:
input
- input X: [x_1, s_1, s_2, …, s_t, input_dim]weight
- weight W: [s_1, s_2, …, s_t, input_dim, units]bias
- bias b: [s_1, s_2, …, s_t, units]- Returns:
- output Y: [x_1, s_1, s_2, …, s_t, units]
-
builder
public static LinearCollection.Builder builder()
Creates a builder to build aLinear
.- Returns:
- a new builder
-
-