public class DeepLearning.DeepLearningDriver extends water.H2O.H2OCountedCompleter<DeepLearning.DeepLearningDriver>
| Constructor and Description |
|---|
DeepLearning.DeepLearningDriver() |
| Modifier and Type | Method and Description |
|---|---|
void |
buildModel()
Train a Deep Learning model, assumes that all members are populated
If checkpoint == null, then start training a new model, otherwise continue from a checkpoint
|
protected void |
compute2() |
DeepLearningModel |
trainModel(DeepLearningModel model)
Train a Deep Learning neural net model
|
clone, compute, frozenType, icer, nextThrPriority, onExceptionalCompletion, priority, read_impl, read, readJSON_impl, readJSON, write_impl, write, writeHTML_impl, writeHTML, writeJSON_impl, writeJSONaddToPendingCount, compareAndSetPendingCount, complete, exec, getCompleter, getPendingCount, getRawResult, onCompletion, setCompleter, setPendingCount, setRawResult, tryCompleteadapt, 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, tryUnforkprotected void compute2()
compute2 in class water.H2O.H2OCountedCompleter<DeepLearning.DeepLearningDriver>public final void buildModel()
public final DeepLearningModel trainModel(DeepLearningModel model)
model - Input model (e.g., from initModel(), or from a previous training run)