hex.deeplearning

Class DeepLearningTask2

java.lang.Object

jsr166y.ForkJoinTask<java.lang.Void>

jsr166y.CountedCompleter

water.H2O.H2OCountedCompleter<T>

water.DTask<T>

water.MRTask<DeepLearningTask2>

hex.deeplearning.DeepLearningTask2

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, java.util.concurrent.Future<java.lang.Void>, jsr166y.ForkJoinPool.ManagedBlocker, water.Freezable

public class DeepLearningTask2
extends water.MRTask<DeepLearningTask2>

DRemoteTask-based Deep Learning. Every node has access to all the training data which leads to optimal CPU utilization IF the data fits on every node.

See Also:

Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class water.DTask

water.DTask.DKeyTask<T extends water.DTask.DKeyTask,V extends water.Keyed>, water.DTask.RemoveCall

Field Summary

Fields inherited from class water.MRTask

_appendables, _fs, _hi, _keys, _left, _lo, _nhi, _nleft, _nrite, _nxx, _rite, _topLocal

Fields inherited from class water.DTask

_ex, _modifiesInputs

Constructor Summary

Constructors

Constructor and Description
DeepLearningTask2(water.Key jobKey, water.fvec.Frame train, DeepLearningModel.DeepLearningModelInfo model_info, float sync_fraction) Construct a DeepLearningTask2 where every node trains on the entire training dataset

Method Summary

Methods

Modifier and Type	Method and Description
DeepLearningModel.DeepLearningModelInfo	model_info() Returns the aggregated DeepLearning model that was trained by all nodes (over all the training data)
protected void	postGlobal() Finish up the work after all nodes have reduced their models via the above reduce() method.
void	reduce(DeepLearningTask2 drt) Reduce between worker nodes, with network traffic (if greater than 1 nodes) After all reduce()'s are done, postGlobal() will be called
void	setupLocal() Do the local computation: Perform one DeepLearningTask (with run_local=true) iteration.

Methods inherited from class water.MRTask

appendables, asyncExec, asyncExec, asyncExec, block, closeLocal, compute2, dfork, dfork, dfork, dfork, dinvoke, doAll, doAll, doAll, doAll, doAll, doAll, doAll, doAllNodes, getResult, isReleasable, map, map, map, map, map, map, map, map, map, map, map, map, map, onCompletion, onExceptionalCompletion, outputFrame, outputFrame, outputFrame, outputFrame, priority, profString, setProfile

Methods inherited from class water.DTask

copyOver, getDException, hasException, logVerbose, onAck, onAckAck, setException

Methods inherited from class water.H2O.H2OCountedCompleter

clone, compute, frozenType, icer, nextThrPriority, read_impl, read, readJSON_impl, readJSON, write_impl, write, writeHTML_impl, writeHTML, writeJSON_impl, writeJSON

Methods inherited from class jsr166y.CountedCompleter

addToPendingCount, compareAndSetPendingCount, complete, exec, getCompleter, getPendingCount, getRawResult, setCompleter, setPendingCount, setRawResult, tryComplete

Methods inherited from class jsr166y.ForkJoinTask

adapt, adapt, adapt, cancel, compareAndSetForkJoinTaskTag, completeExceptionally, fork, get, get, getException, getForkJoinTaskTag, getPool, getQueuedTaskCount, getSurplusQueuedTaskCount, helpQuiesce, inForkJoinPool, invoke, invokeAll, invokeAll, invokeAll, isCancelled, isCompletedAbnormally, isCompletedNormally, isDone, join, peekNextLocalTask, pollNextLocalTask, pollTask, quietlyComplete, quietlyInvoke, quietlyJoin, reinitialize, setForkJoinTaskTag, tryUnfork

Methods inherited from class java.lang.Object

equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

DeepLearningTask2

public DeepLearningTask2(water.Key jobKey,
                 water.fvec.Frame train,
                 DeepLearningModel.DeepLearningModelInfo model_info,
                 float sync_fraction)

Construct a DeepLearningTask2 where every node trains on the entire training dataset

Parameters:

train - Frame containing training data

model_info - Initial DeepLearningModelInfo (weights + biases)

sync_fraction - Fraction of the training data to use for one SGD iteration

Method Detail

model_info

public DeepLearningModel.DeepLearningModelInfo model_info()

Returns the aggregated DeepLearning model that was trained by all nodes (over all the training data)

Returns:

model_info object

setupLocal

public void setupLocal()

Do the local computation: Perform one DeepLearningTask (with run_local=true) iteration. Pass over all the data (will be replicated in dfork() here), and use _sync_fraction random rows. This calls DeepLearningTask's reduce() between worker threads that update the same local model_info via Hogwild! Once the computation is done, reduce() will be called

Overrides:

setupLocal in class water.MRTask<DeepLearningTask2>

reduce

public void reduce(DeepLearningTask2 drt)

Reduce between worker nodes, with network traffic (if greater than 1 nodes) After all reduce()'s are done, postGlobal() will be called

Overrides:

reduce in class water.MRTask<DeepLearningTask2>

Parameters:

drt - task to reduce

postGlobal

protected void postGlobal()

Finish up the work after all nodes have reduced their models via the above reduce() method. All we do is average the models and add to the global training sample counter. After this returns, model_info() can be queried for the updated model.

Overrides:

postGlobal in class water.MRTask<DeepLearningTask2>