Class ResourceApplyFtrl.Inputs<T extends TType>
java.lang.Object
org.tensorflow.op.RawOpInputs<ResourceApplyFtrl>
org.tensorflow.op.train.ResourceApplyFtrl.Inputs<T>
- Enclosing class:
ResourceApplyFtrl
public static class ResourceApplyFtrl.Inputs<T extends TType>
extends RawOpInputs<ResourceApplyFtrl>
-
Field Summary
FieldsModifier and TypeFieldDescriptionShould be from a Variable().The gradient.L1 regularization.L2 shrinkage regularization.The l2Shrinkage inputShould be from a Variable().Scaling factor.Scaling factor.final booleanThe multiplyLinearByLr attributefinal DataTypeThe T attributefinal booleanIfTrue, updating of the var and accum tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention.Should be from a Variable(). -
Constructor Summary
Constructors -
Method Summary
Methods inherited from class RawOpInputs
attributeMetadata, attributeNames, attributes, attributeValue, attributeValues, equals, getOutputs, hashCode, toString
-
Field Details
-
var
-
accum
-
linear
-
grad
-
lr
-
l1
-
l2
-
l2Shrinkage
-
lrPower
-
T
The T attribute -
useLocking
public final boolean useLockingIfTrue, updating of the var and accum tensors will be protected by a lock; otherwise the behavior is undefined, but may exhibit less contention. -
multiplyLinearByLr
public final boolean multiplyLinearByLrThe multiplyLinearByLr attribute
-
-
Constructor Details
-
Inputs
-