org.apache

mxnet

package mxnet

Visibility
  1. Public
  2. All

Type Members

  1. class Accuracy extends EvalMetric

    Calculate accuracy

  2. trait BatchEndCallback extends AnyRef

  3. class CompositeEvalMetric extends EvalMetric

    Manage multiple evaluation metrics.

  4. class Context extends Serializable

    Constructing a context.

  5. class CustomMetric extends EvalMetric

    Custom evaluation metric that takes a NDArray function.

  6. abstract class CustomOp extends AnyRef

    Base class for operators implemented in Scala

  7. abstract class CustomOpProp extends AnyRef

    Base class for operator property class implemented in Scala.

    Base class for operator property class implemented in Scala. MXNET_CPU_WORKER_NTHREADS must be greater than 1 for custom op to work on CPU

  8. class DataBatch extends AnyRef

    class batch of data

  9. case class DataDesc(name: String, shape: Shape, dtype: DType = DType.Float32, layout: String = Layout.UNDEFINED) extends Product with Serializable

  10. abstract class DataIter extends Iterator[DataBatch]

    DataIter object in mxnet.

  11. abstract class DataPack extends Iterable[DataBatch]

    pack of DataIter, use as Iterable class

  12. trait EpochEndCallback extends AnyRef

  13. abstract class EvalMetric extends AnyRef

    Base class of all evaluation metrics

  14. class Executor extends WarnIfNotDisposed

    Symbolic Executor component of MXNet
    WARNING: it is your responsibility to clear this object through dispose().

Symbolic Executor component of MXNet
WARNING: it is your responsibility to clear this object through dispose().

See also

Symbol.bind : to create executor

  • class F1 extends EvalMetric

    Calculate the F1 score of a binary classification problem.

  • class FactorScheduler extends LRScheduler

    Class for reducing learning rate in factor

    Class for reducing learning rate in factor

    Assume the weight has been updated by n times, then the learning rate will be base_lr * factor^^(floor(n/step))

  • class FeedForward extends AnyRef

    Model class of MXNet for training and predicting feedforward nets.

    Model class of MXNet for training and predicting feedforward nets. This class is designed for a single-data single output supervised network.

  • abstract class Initializer extends AnyRef

    Base class for Initializer.

  • class KVStore extends WarnIfNotDisposed

  • abstract class LRScheduler extends AnyRef

    Learning rate scheduler, which adaptively changes the learning rate based on the training progress.

  • class MAE extends EvalMetric

    Calculate Mean Absolute Error loss

  • class MSE extends EvalMetric

  • class MXIndexedRecordIO extends MXRecordIO

    Scala interface for read/write RecordIO data formmat with index.

    Scala interface for read/write RecordIO data formmat with index. Support random access.

  • trait MXKVStoreCachedStates extends AnyRef

  • trait MXKVStoreUpdater extends AnyRef

  • class MXNetError extends Exception

  • class MXRecordIO extends AnyRef

    Scala interface for read/write RecordIO data format

  • class Mixed extends Initializer

    Initialize the weight with mixed Initializer

  • class Model extends AnyRef

    Describe the model flow

  • class Monitor extends AnyRef

    Monitor outputs, weights, and gradients for debugging.

  • class NDArray extends WarnIfNotDisposed

    NDArray object in mxnet.

    NDArray object in mxnet. NDArray is basic ndarray/Tensor like data structure in mxnet.
    WARNING: it is your responsibility to clear this object through dispose().

  • abstract class NDArrayAPIBase extends AnyRef

  • abstract class NDArrayBase extends AnyRef

  • class NDArrayCollector extends AnyRef

  • class NameManager extends AnyRef

    NameManager to do automatic naming.

    NameManager to do automatic naming. User can also inherit this object to change naming behavior.

  • class Normal extends Initializer

    Initialize the weight with normal(0, sigma)

  • abstract class Optimizer extends Serializable

  • class Perplexity extends EvalMetric

    Calculate perplexity.

  • class RMSE extends EvalMetric

    Calculate Root Mean Squred Error loss

  • class Rtc extends AnyRef

    This class allow you to write cuda kernel in Scala and call them with NDArray.

  • class Shape extends Serializable

    Shape of NDArray or other data

  • class Symbol extends WarnIfNotDisposed

    Symbolic configuration API of mxnet.

    Symbolic configuration API of mxnet.
    WARNING: it is your responsibility to clear this object through dispose().

  • abstract class SymbolAPIBase extends AnyRef

  • abstract class SymbolBase extends AnyRef

  • class SymbolConversions[V] extends AnyRef

  • trait SymbolGenerator extends AnyRef

  • class TestUtil extends AnyRef

  • class TopKAccuracy extends EvalMetric

    Calculate top k predictions accuracy

  • class Uniform extends Initializer

    Initialize the weight with uniform [-scale, scale]

  • trait WarnIfNotDisposed extends AnyRef

    Attributes
    protected
  • class Xavier extends Initializer

    Initialize the weight with Xavier or similar initialization scheme.

  • Value Members

    1. object Callback

      Callback functions that can be used to track various status during epoch.

    2. object CheckUtils

    3. object Context extends Serializable

    4. object DType extends Enumeration

    5. object DataBatch

    6. object DataDesc extends Serializable

    7. object Executor

    8. object FeedForward

    9. object IO

      IO iterators for loading training & validation data

    10. object KVStore

      Key value store interface of MXNet for parameter synchronization.

    11. object KVStoreServer

    12. object Layout

      Layout definition of DataDesc N Batch size C channels H Height W Weight T sequence length undefined default value of Layout

    13. object MXRecordIO

    14. object Model

    15. object NDArray extends NDArrayBase

      NDArray Object extends from NDArrayBase for abstract function signatures Main code will be generated during compile time through Macros

    16. object NDArrayAPI extends NDArrayAPIBase

    17. object NDArrayCollector

      A collector to store NDArrays.

      A collector to store NDArrays. It provides a scope, NDArrays allocated in the scope can either

      • be disposed automatically when the code block finishes, or
      • simply be collected for future usage.
        If the return type of scope is NDArray or NDArrayFuncReturn, the collector is smart enough NOT to collect or dispose the returned NDArray.
        However in other cases, it is users' responsibility NOT to leak allocated NDArrays outside, (e.g., store to a global variable and use later, pass to another thread, etc.)
        Usage Example:
         val a = NDArray.array(Array(-1f, 0f, 1f, 2f, 3f, 4f), shape = Shape(2, 3))
         val res = NDArrayCollector.auto().withScope {
           (NDArray.relu(a) + a).toArray
         }
        
        In the case above, the intermediate NDArrays (created by NDArray.relu and +) will be disposed automatically.
        User can also decide to dispose the collected NDArrays later:
         val collector = NDArrayCollector.manual()
         val res = collector.withScope {
           (NDArray.relu(a) + a).toArray
         }
         collector.foreach(_.dispose())
        
        For Java users:
         NDArray a = NDArray.array(new float[]{-1f, 0f, 1f, 2f, 3f, 4f},
                                   Shape.create(2, 3), Context.cpu(0));
         float[] sliced = NDArrayCollector.auto().withScope(
           new scala.runtime.AbstractFunction0() {
           @Override
           public float[] apply() {
             a.slice(0, 1).toArray();
           }
         });
        
    18. object NameManager

    19. object Operator

    20. object Optimizer extends Serializable

    21. object Profiler

    22. object Random

      Random Number interface of mxnet.

    23. object Shape extends Serializable

    24. object Symbol extends SymbolBase

      Symbol Object extends from SymbolBase for abstract function signatures Main code will be generated during compile time through Macros

    25. object SymbolAPI extends SymbolAPIBase

    26. object SymbolConversions

    27. object Visualization

    28. package annotation

    29. package contrib

    30. package infer

    31. package io

    32. package module

    33. package optimizer

    Ungrouped