Predictor

Instance Constructors

new Predictor(modelPathPrefix: String, inputDescriptors: IndexedSeq[DataDesc], contexts: Array[Context] = Context.cpu(), epoch: Option[Int] = Some(0))

modelPathPrefix
Path prefix from where to load the model artifacts. These include the symbol, parameters, and synset.txt Example: file://model-dir/resnet-152 (containing resnet-152-symbol.json, resnet-152-0000.params, and synset.txt).
inputDescriptors
Descriptors defining the input node names, shape, layout and type parameters
Note: If the input Descriptors is missing batchSize ('N' in layout), a batchSize of 1 is assumed for the model.
contexts
Device contexts on which you want to run inference; defaults to CPU
epoch
Model epoch to load; defaults to 0

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
var batchIndex: Int

Attributes
protected[org.apache.mxnet.infer]
var batchSize: Int

Attributes
protected[org.apache.mxnet.infer]
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
val contexts: Array[Context]

Device contexts on which you want to run inference; defaults to CPU
Device contexts on which you want to run inference; defaults to CPU

Attributes
protected
val epoch: Option[Int]

Model epoch to load; defaults to 0
Model epoch to load; defaults to 0

Attributes
protected
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
var iDescriptors: IndexedSeq[DataDesc]

Attributes
protected[org.apache.mxnet.infer]
val inputDescriptors: IndexedSeq[DataDesc]

Descriptors defining the input node names, shape, layout and type parameters
Descriptors defining the input node names, shape, layout and type parameters
Note: If the input Descriptors is missing batchSize ('N' in layout), a batchSize of 1 is assumed for the model.

Attributes
protected
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
val mod: Module

Attributes
protected[org.apache.mxnet.infer]
val mxNetHandler: MXNetHandler

Attributes
protected[org.apache.mxnet.infer]
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def outputShapes: IndexedSeq[(String, Shape)]

Get model output shapes.
Get model output shapes.
returns
model output shapes.

Definition Classes
Predictor → PredictBase
def predict[T](input: IndexedSeq[Array[T]]): IndexedSeq[Array[T]]

Takes input as IndexedSeq one dimensional arrays and creates the NDArray needed for inference The array will be reshaped based on the input descriptors.
Takes input as IndexedSeq one dimensional arrays and creates the NDArray needed for inference The array will be reshaped based on the input descriptors.
T
The Scala equivalent of the DType used for the input array and return value
returns
Indexed sequence array of outputs

Definition Classes
Predictor → PredictBase
def predictWithNDArray(inputBatch: IndexedSeq[NDArray]): IndexedSeq[NDArray]

Predict using NDArray as input This method is useful when the input is a batch of data Note: User is responsible for managing allocation/deallocation of input/output NDArrays.
Predict using NDArray as input This method is useful when the input is a batch of data Note: User is responsible for managing allocation/deallocation of input/output NDArrays.
inputBatch
IndexedSequence NDArrays
returns
Output of predictions as NDArrays

Definition Classes
Predictor → PredictBase
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toString(): String

Definition Classes
AnyRef → Any
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

Related Doc: package infer

class Predictor extends PredictBase

Instance Constructors

new Predictor(modelPathPrefix: String, inputDescriptors: IndexedSeq[DataDesc], contexts: Array[Context] = Context.cpu(), epoch: Option[Int] = Some(0))

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

var batchIndex: Int

var batchSize: Int

def clone(): AnyRef

val contexts: Array[Context]

val epoch: Option[Int]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

var iDescriptors: IndexedSeq[DataDesc]

val inputDescriptors: IndexedSeq[DataDesc]

final def isInstanceOf[T0]: Boolean

val mod: Module

val mxNetHandler: MXNetHandler

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def outputShapes: IndexedSeq[(String, Shape)]

def predict[T](input: IndexedSeq[Array[T]]): IndexedSeq[Array[T]]

def predictWithNDArray(inputBatch: IndexedSeq[NDArray]): IndexedSeq[NDArray]

final def synchronized[T0](arg0: ⇒ T0): T0

def toString(): String

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from PredictBase

Inherited from AnyRef

Inherited from Any

Ungrouped