All Classes

Class	Description
AbstractActivation	Abstract base class for Activations
AbstractConstraint	Base class for Constraints.
AbstractRegularizer	Base class for Regularizers
Accuracy<T extends TNumber>	Metric that calculates how often predictions equals labels.
Activation	Interface for Activations
Activations	The Enumerations for creating Activations based an activation name, with either an empty constructor or a constructor that takes a Map object that contains the Activation's state.
AdaDelta	Optimizer that implements the Adadelta algorithm.
AdaGrad	Optimizer that implements the Adagrad algorithm.
AdaGradDA	Optimizer that implements the Adagrad Dual-Averaging algorithm.
Adam	Optimizer that implements the Adam algorithm.
Adamax	Optimizer that implements the Adamax algorithm.
AUC<T extends TNumber>	Metric that computes the approximate AUC (Area under the curve) via a Riemann sum.
AUCCurve	Specifies the type of the curve to be computed, AUCCurve.ROC for a Receiver Operator Characteristic curve [default] or AUCCurve.PR for a Precision-Recall-curve.
AUCSummationMethod	Specifies the Riemann summation method used.
Axes	Axes Operations
BaseInitializer<T extends TType>	Abstract base class for all Initializers
BaseMetric	Base class for Metrics
BinaryAccuracy<T extends TNumber>	Metric that calculates how often predictions matches binary labels.
BinaryCrossentropy	Computes the cross-entropy loss between true labels and predicted labels.
BinaryCrossentropy<T extends TNumber>	A Metric that computes the binary cross-entropy loss between true labels and predicted labels.
CastHelper	A helper class for casting an Operand
CategoricalAccuracy<T extends TNumber>	Metric that calculates how often predictions matches one-hot labels.
CategoricalCrossentropy	Computes the crossentropy loss between the labels and predictions.
CategoricalCrossentropy<T extends TNumber>	A Metric that computes the categorical cross-entropy loss between true labels and predicted labels.
CategoricalHinge	Computes the categorical hinge loss between labels and predictions.
CategoricalHinge<T extends TNumber>	A Metric that computes the categorical hinge loss metric between labels and predictions.
ConfusionMatrix	Confusion Matrix Operations
Constant<T extends TType>	Initializer that generates tensors with a constant value.
Constraint
CosineSimilarity	Computes the cosine similarity between labels and predictions.
CosineSimilarity<T extends TNumber>	A metric that computes the cosine similarity metric between labels and predictions.
Dataset	Represents a potentially large list of independent elements (samples), and allows iteration and transformations to be performed across these elements.
DatasetIterator	Represents the state of an iteration through a tf.data Datset.
DatasetOptional	An optional represents the result of a dataset getNext operation that may fail, when the end of the dataset has been reached.
ELU	Exponential linear unit.
Exponential	Exponential activation function.
FalseNegatives<T extends TNumber>	Metric that calculates the number of false negatives.
FalsePositives<T extends TNumber>	Metric that calculates the number of false positives.
FrameworkOps	An API for building framework operations as Ops
Ftrl	Optimizer that implements the FTRL algorithm.
GELU	Applies the Gaussian error linear unit (GELU) activation function.
GELU	The Gaussian Error Linear Unit (GELU) activation function.
Glorot<T extends TFloating>	The Glorot initializer, also called Xavier initializer.
GradientDescent	Basic Stochastic gradient descent optimizer.
HardSigmoid	Hard sigmoid activation.
He<T extends TFloating>	He initializer.
Hinge	Computes the hinge loss between labels and predictions.
Hinge<T extends TNumber>	A metric that computes the hinge loss metric between labels and predictions.
Huber	Computes the Huber loss between labels and predictions.
Identity<T extends TFloating>	Initializer that generates the identity matrix.
Initializer<T extends TType>	An interface for Initializers
KLDivergence	Computes Kullback-Leibler divergence loss between labels and predictions.
KLDivergence<T extends TNumber>	A metric that computes the Kullback-Leibler divergence loss metric between labels and predictions.
L1	A regularizer that applies an L1 or Lasso(least absolute shrinkage and selection operator) Regression, regularization penalty.
L1L2	A regularizer that applies both L1 and L2 regularization penalties.
L2	A regularizer that applies a L2 (Ridge Regression) regularization penalty.
L2Normalize	L2 Normalization Operations
LeCun<T extends TFloating>	LeCun normal initializer.
LinalgOps
Linear	Linear activation function (pass-through).
LogCosh	Computes Computes the logarithm of the hyperbolic cosine of the prediction error.
LogCoshError<T extends TNumber>	A metric that computes the logarithm of the hyperbolic cosine of the prediction error metric between labels and predictions.
Loss	Interface for loss calc ulation
Losses	Built-in loss functions.
MathOps
MatMul	Multiplication matrix operations
MaxNorm	Constrains the weights incident to each hidden unit to have a norm less than or equal to a desired value.
Mean<T extends TNumber>	A metric that that implements a weighted mean MetricReduction.WEIGHTED_MEAN
MeanAbsoluteError	Computes the mean of absolute difference between labels and predictions.
MeanAbsoluteError<T extends TNumber>	A metric that computes the mean of absolute difference between labels and predictions.
MeanAbsolutePercentageError	Computes the mean absolute percentage error between labels and predictions.
MeanAbsolutePercentageError<T extends TNumber>	A metric that computes the mean of absolute difference between labels and predictions.
MeanIoU<T extends TNumber>	Computes the mean Intersection-Over-Union metric.
MeanRelativeError<T extends TNumber>	Computes the mean relative error by normalizing with the given values.
MeanSquaredError	Computes the mean of squares of errors between labels and predictions.
MeanSquaredError<T extends TNumber>	A metric that computes the mean of absolute difference between labels and predictions.
MeanSquaredLogarithmicError	Computes the mean squared logarithmic errors between labels and predictions.
MeanSquaredLogarithmicError<T extends TNumber>	A metric that computes the mean of absolute difference between labels and predictions.
MeanTensor<T extends TNumber>	Metric that computes the element-wise (weighted) mean of the given tensors.
Metric	Interface for metrics
MetricReduction	Defines the different types of metric reductions
Metrics	Static methods for computing metrics.
MinMaxNorm	Constrains the weights to have the norm between a lower bound and an upper bound.
Momentum	Stochastic gradient descent plus momentum, either nesterov or traditional.
Nadam	Nadam Optimizer that implements the NAdam algorithm.
NnOps	Creates Framework nerual network Operations
NonNeg	Constrains the weights to be non-negative.
NotBroadcastableException	Exception that indicates that static shapes are not able to broadcast among each other during arithmetic operations.
Ones<T extends TType>	Initializer that generates tensors initialized to 1.
Optimizer	Base class for gradient optimizers.
Optimizer.GradAndVar<T extends TType>	A class that holds a paired gradient and variable.
Optimizer.Options	Optional attributes for Optimizer
Optimizers	Enumerator used to create a new Optimizer with default parameters.
Orthogonal<T extends TFloating>	Initializer that generates an orthogonal matrix.
Poisson	Computes the Poisson loss between labels and predictions.
Poisson<T extends TNumber>	A metric that computes the poisson loss metric between labels and predictions.
Precision<T extends TNumber>	Computes the precision of the predictions with respect to the labels.
PrecisionAtRecall<T extends TNumber>	Computes best precision where recall is >= specified value.
RandomNormal<T extends TFloating>	Initializer that generates tensors with a normal distribution.
RandomUniform<T extends TNumber>	Initializer that generates tensors with a uniform distribution.
Recall<T extends TNumber>	Computes the recall of the predictions with respect to the labels.
RecallAtPrecision<T extends TNumber>	Computes best recall where precision is >= specified value.
ReduceLogSumExp	Reduce Log Sum Exp Operations
Reduction	Type of AbstractLoss Reduction
Regularizer
ReLU	Rectified Linear Unit(ReLU) activation.
RMSProp	Optimizer that implements the RMSProp algorithm.
RootMeanSquaredError<T extends TNumber>	Computes root mean squared error metric between labels and predictions .
SELU	Scaled Exponential Linear Unit (SELU).
SensitivityAtSpecificity<T extends TNumber>	Computes best sensitivity where sensitivity is >= specified value.
SetOps	Creates Framework set Operations
Sets
Sets.Operation	Enumeration containing the string operation values to be passed to the TensorFlow Sparse Ops function SparseOps.denseToDenseSetOperation(org.tensorflow.Operand<T>, org.tensorflow.Operand<T>, java.lang.String, org.tensorflow.op.sparse.DenseToDenseSetOperation.Options...)
ShapeUtils	Various methods for processing with Shapes and Operands
Sigmoid	Sigmoid activation.
SigmoidCrossEntropyWithLogits
Softmax	Softmax converts a real vector to a vector of categorical probabilities.
SoftmaxCrossEntropyWithLogits
Softplus	Softplus activation function, softplus(x) = log(exp(x) + 1).
Softsign	Softsign activation function, softsign(x) = x / (abs(x) + 1).
SparseCategoricalAccuracy<T extends TNumber>	Calculates how often predictions matches integer labels.
SparseCategoricalCrossentropy	Computes the crossentropy loss between labels and predictions.
SparseCategoricalCrossentropy<T extends TNumber>	A metric that computes the sparse categorical cross-entropy loss between true labels and predicted labels.
SparseSoftmaxCrossEntropyWithLogits
SparseTensor<T extends TType>	This is a helper class that represents a sparse tensor who's attributes may be passed to SparseOps methods.
SparseTopKCategoricalAccuracy<T extends TNumber>	Computes how often integer targets are in the top `K` predictions.
SpecificityAtSensitivity<T extends TNumber>	Computes best specificity where sensitivity is >= specified value.
SquaredHinge	Computes the squared hinge loss between labels and predictions.
SquaredHinge<T extends TNumber>	A metric that computes the squared hinge loss metric between labels and predictions.
Sum<T extends TNumber>	Computes the (weighted) sum of the given values.
Swish	Swish activation function.
Tanh	Hyperbolic tangent activation function.
TensorDot	tensor contraction Operations
TopKCategoricalAccuracy<T extends TNumber>	Computes the poisson loss metric between labels and predictions.
TrueNegatives<T extends TNumber>	Metric that calculates the number of true negatives.
TruePositives<T extends TNumber>	Metric that calculates the number of true positives.
TruncatedNormal<T extends TFloating>	Initializer that generates a truncated normal distribution.
UnitNorm	Constrains the weights to have unit norm.
VarianceScaling<T extends TFloating>	Initializer capable of adapting its scale to the shape of weights tensors.
VarianceScaling.Distribution	The random distribution to use when initializing the values.
VarianceScaling.Mode	The mode to use for calculating the fan values.
Zeros<T extends TType>	Creates an Initializer that sets all values to zero.