public final class BoostedTreesSparseAggregateStats extends PrimitiveOp
The summary stats contains gradients and hessians accumulated for each node, bucket and dimension id.
operation
Modifier and Type | Method and Description |
---|---|
static BoostedTreesSparseAggregateStats |
create(Scope scope,
Operand<Integer> nodeIds,
Operand<Float> gradients,
Operand<Float> hessians,
Operand<Integer> featureIndices,
Operand<Integer> featureValues,
Operand<Integer> featureShape,
Long maxSplits,
Long numBuckets)
Factory method to create a class wrapping a new BoostedTreesSparseAggregateStats operation.
|
Output<Integer> |
statsSummaryIndices()
int32; Rank 2 indices of summary sparse Tensors (shape=[number of non zero statistics, 4])
The second axis can only be 4 including node id, feature dimension, bucket id, and statistics_dimension.
|
Output<Integer> |
statsSummaryShape()
output Rank 1 Tensor (shape=[4])
The tensor has following 4 values: [max_splits, feature_dimension, num_buckets, statistics_dimension],
where statistics_dimension = gradient_dimension + hessian_dimension.
|
Output<Float> |
statsSummaryValues()
output Rank 1 Tensor (shape=[number of non zero statistics])
|
equals, hashCode, op, toString
public static BoostedTreesSparseAggregateStats create(Scope scope, Operand<Integer> nodeIds, Operand<Float> gradients, Operand<Float> hessians, Operand<Integer> featureIndices, Operand<Integer> featureValues, Operand<Integer> featureShape, Long maxSplits, Long numBuckets)
scope
- current scopenodeIds
- int32; Rank 1 Tensor containing node ids for each example, shape [batch_size].gradients
- float32; Rank 2 Tensor (shape=[batch_size, logits_dimension]) with gradients for each example.hessians
- float32; Rank 2 Tensor (shape=[batch_size, hessian_dimension]) with hessians for each example.featureIndices
- int32; Rank 2 indices of feature sparse Tensors (shape=[number of sparse entries, 2]).
Number of sparse entries across all instances from the batch. The first value is
the index of the instance, the second is dimension of the feature. The second axis
can only have 2 values, i.e., the input dense version of Tensor can only be matrix.featureValues
- int32; Rank 1 values of feature sparse Tensors (shape=[number of sparse entries]).
Number of sparse entries across all instances from the batch. The first value is
the index of the instance, the second is dimension of the feature.featureShape
- int32; Rank 1 dense shape of feature sparse Tensors (shape=[2]).
The first axis can only have 2 values, [batch_size, feature_dimension].maxSplits
- int; the maximum number of splits possible in the whole tree.numBuckets
- int; equals to the maximum possible value of bucketized feature + 1.public Output<Integer> statsSummaryIndices()
public Output<Float> statsSummaryValues()
public Output<Integer> statsSummaryShape()
Copyright © 2022. All rights reserved.