public class Dropout extends ParameterBlock
During training, each element of the input is set to zero with probability p. The whole array is rescaled by 1/(1−p) to keep the expected sum of the input unchanged. During testing, this dropout does not change the input if mode is ‘training’. If mode is ‘always’, the same computation as during training will be applied.
Modifier and Type | Class and Description |
---|---|
static class |
Dropout.Builder
|
inputNames, inputShapes
Modifier and Type | Method and Description |
---|---|
static Dropout.Builder |
builder()
Creates a builder to build a
Dropout . |
NDList |
forward(ParameterStore parameterStore,
NDList inputs,
ai.djl.util.PairList<java.lang.String,java.lang.Object> params)
Applies the operating function of the block once.
|
java.util.List<Parameter> |
getDirectParameters()
Returns a list of all the direct parameters of the block.
|
Shape[] |
getOutputShapes(NDManager manager,
Shape[] inputShapes)
Returns the expected output shapes of the block for the specified input shapes.
|
Shape |
getParameterShape(java.lang.String name,
Shape[] inputShapes)
Returns the shape of the specified direct parameter of this block given the shapes of the
input to the block.
|
void |
loadParameters(NDManager manager,
java.io.DataInputStream is)
Loads the parameters from the given input stream.
|
void |
saveParameters(java.io.DataOutputStream os)
Writes the parameters of the block to the given outputStream.
|
getChildren, initialize, toString
beforeInitialize, cast, clear, describeInput, getParameters, isInitialized, readInputShapes, saveInputShapes, setInitializer, setInitializer
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
forward, validateLayout
public NDList forward(ParameterStore parameterStore, NDList inputs, ai.djl.util.PairList<java.lang.String,java.lang.Object> params)
parameterStore
- the parameter storeinputs
- the input NDListparams
- optional parameterspublic Shape[] getOutputShapes(NDManager manager, Shape[] inputShapes)
manager
- an NDManagerinputShapes
- the shapes of the inputspublic java.util.List<Parameter> getDirectParameters()
Parameter
public Shape getParameterShape(java.lang.String name, Shape[] inputShapes)
name
- the name of the parameterinputShapes
- the shapes of the input to the blockpublic void saveParameters(java.io.DataOutputStream os) throws java.io.IOException
os
- the outputstream to save the parameters tojava.io.IOException
- if an I/O error occurspublic void loadParameters(NDManager manager, java.io.DataInputStream is) throws java.io.IOException, MalformedModelException
manager
- an NDManager to create the parameter arraysis
- the inputstream that stream the parameter valuesjava.io.IOException
- if an I/O error occursMalformedModelException
- if the model file is corrupted or unsupportedpublic static Dropout.Builder builder()
Dropout
.