BoostedTreesTrainingPredict

public final class BoostedTreesTrainingPredict

Runs multiple additive regression ensemble predictors on input instances and

computes the update to cached logits. It is designed to be used during training. It traverses the trees starting from cached tree id and cached node id and calculates the updates to be pushed to the cache.

Public Methods

static BoostedTreesTrainingPredict
create(Scope scope, Operand<?> treeEnsembleHandle, Operand<Integer> cachedTreeIds, Operand<Integer> cachedNodeIds, Iterable<Operand<Integer>> bucketizedFeatures, Long logitsDimension)
Factory method to create a class wrapping a new BoostedTreesTrainingPredict operation.
Output<Integer>
nodeIds()
Rank 1 Tensor containing new node ids in the new tree_ids.
Output<Float>
partialLogits()
Rank 2 Tensor containing logits update (with respect to cached values stored) for each example.
Output<Integer>
treeIds()
Rank 1 Tensor containing new tree ids for each example.

Inherited Methods

Public Methods

public static BoostedTreesTrainingPredict create (Scope scope, Operand<?> treeEnsembleHandle, Operand<Integer> cachedTreeIds, Operand<Integer> cachedNodeIds, Iterable<Operand<Integer>> bucketizedFeatures, Long logitsDimension)

Factory method to create a class wrapping a new BoostedTreesTrainingPredict operation.

Parameters
scope current scope
cachedTreeIds Rank 1 Tensor containing cached tree ids which is the starting tree of prediction.
cachedNodeIds Rank 1 Tensor containing cached node id which is the starting node of prediction.
bucketizedFeatures A list of rank 1 Tensors containing bucket id for each feature.
logitsDimension scalar, dimension of the logits, to be used for partial logits shape.
Returns
  • a new instance of BoostedTreesTrainingPredict

public Output<Integer> nodeIds ()

Rank 1 Tensor containing new node ids in the new tree_ids.

public Output<Float> partialLogits ()

Rank 2 Tensor containing logits update (with respect to cached values stored) for each example.

public Output<Integer> treeIds ()

Rank 1 Tensor containing new tree ids for each example.