Packages

trait NN extends AnyRef

Linear Supertypes
AnyRef, Any
Known Subclasses
NN
Ordering
  1. Alphabetic
  2. By Inheritance
Inherited
  1. NN
  2. AnyRef
  3. Any
  1. Hide All
  2. Show All
Visibility
  1. Public
  2. All

Value Members

  1. final def !=(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  2. final def ##(): Int
    Definition Classes
    AnyRef → Any
  3. final def ==(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  4. def addBias[T](value: Output[T], bias: Output[T], cNNDataFormat: CNNDataFormat = CNNDataFormat.default, name: String = "AddBias")(implicit arg0: core.types.TF[T], arg1: core.types.IsNumeric[T]): Output[T]
  5. def addBiasGradient[T](op: Op[(Output[T], Output[T]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsNumeric[T]): (Output[T], Output[T])
    Attributes
    protected
  6. def addBiasHessian[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsNumeric[T]): Output[T]
    Attributes
    protected
  7. final def asInstanceOf[T0]: T0
    Definition Classes
    Any
  8. def batchNormalization[T](x: Output[T], mean: Output[T], variance: Output[T], offset: Option[Output[T]] = None, scale: Option[Output[T]] = None, epsilon: Output[T], name: String = "BatchNormalization")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  9. def clone(): AnyRef
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @native() @throws( ... )
  10. def conv2D[T](input: Output[T], filter: Output[T], stride1: Long, stride2: Long, padding: ConvPaddingMode, dataFormat: CNNDataFormat = CNNDataFormat.default, dilations: (Int, Int, Int, Int) = (1, 1, 1, 1), useCuDNNOnGPU: Boolean = true, name: String = "Conv2D")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  11. def conv2DBackpropFilter[T](input: Output[T], filterSizes: Output[Int], outputGradient: Output[T], stride1: Long, stride2: Long, padding: ConvPaddingMode, dataFormat: CNNDataFormat = CNNDataFormat.default, dilations: (Int, Int, Int, Int) = (1, 1, 1, 1), useCuDNNOnGPU: Boolean = true, name: String = "Conv2DBackpropFilter")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  12. def conv2DBackpropInput[T](inputSizes: Output[Int], filter: Output[T], outputGradient: Output[T], stride1: Long, stride2: Long, padding: ConvPaddingMode, dataFormat: CNNDataFormat = CNNDataFormat.default, dilations: (Int, Int, Int, Int) = (1, 1, 1, 1), useCuDNNOnGPU: Boolean = true, name: String = "Conv2DBackpropInput")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  13. def conv2DGradient[T](op: Op[(Output[T], Output[T]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): (Output[T], Output[T])
    Attributes
    protected
  14. def crelu[T](input: Output[T], axis: Output[Int] = -1, name: String = "CReLU")(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): Output[T]
  15. def dropout[T, I](input: Output[T], keepProbability: Float, scaleOutput: Boolean = true, noiseShape: Output[I] = null, seed: Option[Int] = None, name: String = "Dropout")(implicit arg0: core.types.TF[T], arg1: core.types.IsHalfOrFloatOrDouble[T], arg2: IntDefault[I], arg3: core.types.TF[I], arg4: core.types.IsIntOrLong[I]): Output[T]
    Annotations
    @throws( ... )
  16. def dynamicDropout[T, I](input: Output[T], keepProbability: Output[T], scaleOutput: Boolean = true, noiseShape: Output[I] = null, seed: Option[Int] = None, name: String = "Dropout")(implicit arg0: core.types.TF[T], arg1: core.types.IsHalfOrFloatOrDouble[T], arg2: IntDefault[I], arg3: core.types.TF[I], arg4: core.types.IsIntOrLong[I]): Output[T]
  17. def elu[T, OL[A] <: OutputLike[A]](input: OL[T], name: String = "ELU")(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T], ev: Aux[OL, T]): OL[T]
  18. def eluGradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): Output[T]
    Attributes
    protected
  19. def eluHessian[T](op: Op[(Output[T], Output[T]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): (Output[T], Output[T])
    Attributes
    protected
  20. final def eq(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  21. def equals(arg0: Any): Boolean
    Definition Classes
    AnyRef → Any
  22. def finalize(): Unit
    Attributes
    protected[java.lang]
    Definition Classes
    AnyRef
    Annotations
    @throws( classOf[java.lang.Throwable] )
  23. def fusedBatchNormalization[T](x: Output[T], scale: Output[Float], offset: Output[Float], mean: Option[Output[Float]] = None, variance: Option[Output[Float]] = None, epsilon: Float = 0.0001f, dataFormat: CNNDataFormat = NWCFormat, isTraining: Boolean = true, name: String = "FusedBatchNormalization")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): (Output[T], Output[Float], Output[Float], Output[Float], Output[Float])
    Annotations
    @throws( ... )
  24. def fusedBatchNormalizationGradient[T](op: Op[(Output[T], Output[Float], Output[Float], Output[Float], Output[Float]), (Output[T], Output[Float], Output[Float], Output[Float], Output[Float])], outputGradient: (Output[T], Output[Float], Output[Float], Output[Float], Output[Float]))(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): (Output[T], Output[Float], Output[Float], Output[Float], Output[Float])
    Attributes
    protected
  25. final def getClass(): Class[_]
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  26. def hashCode(): Int
    Definition Classes
    AnyRef → Any
    Annotations
    @native()
  27. def inTopK[I](predictions: Output[Float], targets: Output[I], k: Output[I], name: String = "InTopK")(implicit arg0: core.types.TF[I], arg1: core.types.IsIntOrLong[I]): Output[Boolean]
  28. final def isInstanceOf[T0]: Boolean
    Definition Classes
    Any
  29. def l2Loss[T](input: Output[T], name: String = "L2Loss")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  30. def l2LossGradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
    Attributes
    protected
  31. def l2Normalize[T, I](x: Output[T], axes: Output[I], epsilon: Float = 1e-12f, name: String = "L2Normalize")(implicit arg0: core.types.TF[T], arg1: core.types.IsNotQuantized[T], arg2: core.types.TF[I], arg3: core.types.IsIntOrLong[I]): Output[T]
  32. def linear[T](x: Output[T], weights: Output[T], bias: Output[T] = null, name: String = "Linear")(implicit arg0: core.types.TF[T], arg1: core.types.IsNotQuantized[T]): Output[T]
  33. def localResponseNormalization[T](input: Output[T], depthRadius: Int = 5, bias: Float = 1.0f, alpha: Float = 1.0f, beta: Float = 0.5f, name: String = "LocalResponseNormalization")(implicit arg0: core.types.TF[T], arg1: core.types.IsTruncatedHalfOrHalfOrFloat[T]): Output[T]
  34. def logPoissonLoss[T](logPredictions: Output[T], targets: Output[T], computeFullLoss: Boolean = false, name: String = "LogPoissonLoss")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  35. def logSoftmax[T](logits: Output[T], axis: Int = -1, name: String = "LogSoftmax")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  36. def logSoftmaxGradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
    Attributes
    protected
  37. def lrn[T](input: Output[T], depthRadius: Int = 5, bias: Float = 1.0f, alpha: Float = 1.0f, beta: Float = 0.5f, name: String = "LRN")(implicit arg0: core.types.TF[T], arg1: core.types.IsTruncatedHalfOrHalfOrFloat[T]): Output[T]
  38. def lrnGradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsTruncatedHalfOrHalfOrFloat[T]): Output[T]
    Attributes
    protected
  39. def maxPool[T](input: Output[T], windowSize: Output[Int], strides: Output[Int], padding: ConvPaddingMode, dataFormat: CNNDataFormat = CNNDataFormat.default, name: String = "MaxPool")(implicit arg0: core.types.TF[T], arg1: core.types.IsNumeric[T]): Output[T]
  40. def maxPoolGrad[T](originalInput: Output[T], originalOutput: Output[T], outputGradient: Output[T], windowSize: Output[Int], strides: Output[Int], padding: ConvPaddingMode, dataFormat: CNNDataFormat = CNNDataFormat.default, name: String = "MaxPoolGrad")(implicit arg0: core.types.TF[T], arg1: core.types.IsNumeric[T]): Output[T]
  41. def maxPoolGradGrad[T](originalInput: Output[T], originalOutput: Output[T], outputGradient: Output[T], windowSize: Output[Int], strides: Output[Int], padding: ConvPaddingMode, dataFormat: CNNDataFormat = CNNDataFormat.default, name: String = "MaxPoolGradGrad")(implicit arg0: core.types.TF[T], arg1: core.types.IsNumeric[T]): Output[T]
  42. def maxPoolGradient[T](op: Op[(Output[T], Output[Int], Output[Int]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsNumeric[T]): (Output[T], Output[Int], Output[Int])
    Attributes
    protected
  43. def maxPoolHessian[T](op: Op[(Output[T], Output[T], Output[T], Output[Int], Output[Int]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsNumeric[T]): (Output[T], Output[T], Output[T], Output[Int], Output[Int])
    Attributes
    protected
  44. def maxPoolHessianGradient[T](op: Op[(Output[T], Output[T], Output[T], Output[Int], Output[Int]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsNumeric[T]): (Output[T], Output[T], Output[T], Output[Int], Output[Int])
    Attributes
    protected
  45. final def ne(arg0: AnyRef): Boolean
    Definition Classes
    AnyRef
  46. final def notify(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  47. final def notifyAll(): Unit
    Definition Classes
    AnyRef
    Annotations
    @native()
  48. def relu[T](input: Output[T], alpha: Float = 0.0f, name: String = "ReLU")(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): Output[T]
  49. def relu6[T, OL[A] <: OutputLike[A]](input: OL[T], name: String = "ReLU6")(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T], ev: Aux[OL, T]): OL[T]
  50. def relu6Gradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): Output[T]
    Attributes
    protected
  51. def relu6Hessian[T](op: Op[(Output[T], Output[T]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): (Output[T], Output[T])
    Attributes
    protected
  52. def reluGradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): Output[T]
    Attributes
    protected
  53. def reluHessian[T](op: Op[(Output[T], Output[T]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): (Output[T], Output[T])
    Attributes
    protected
  54. def selu[T, OL[A] <: OutputLike[A]](input: OL[T], name: String = "SELU")(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T], ev: Aux[OL, T]): OL[T]
  55. def seluGradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): Output[T]
    Attributes
    protected
  56. def seluHessian[T](op: Op[(Output[T], Output[T]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): (Output[T], Output[T])
    Attributes
    protected
  57. def sequenceLoss[T, L](logits: Output[T], labels: Output[L], lossFn: (Output[T], Output[L]) ⇒ Output[T], weights: Output[T] = null, averageAcrossTimeSteps: Boolean = true, averageAcrossBatch: Boolean = true, name: String = "SequenceLoss")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T], arg2: core.types.TF[L]): Output[T]
    Annotations
    @throws( ... )
  58. def sigmoidCrossEntropy[T](logits: Output[T], labels: Output[T], weights: Output[T] = null, name: String = "SigmoidCrossEntropy")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  59. def softmax[T](logits: Output[T], axis: Int = -1, name: String = "Softmax")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  60. def softmaxCrossEntropy[T](logits: Output[T], labels: Output[T], axis: Int = -1, name: String = "SoftmaxCrossEntropy")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
  61. def softmaxCrossEntropyGradient[T](op: Op[(Output[T], Output[T]), (Output[T], Output[T])], outputGradient: (Output[T], Output[T]))(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): (Output[T], Output[T])
    Attributes
    protected
  62. def softmaxGradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
    Attributes
    protected
  63. def softmaxHelper[T](logits: Output[T], opType: String, axis: Int = -1, name: String = "Softmax")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
    Attributes
    protected
  64. def softplus[T, OL[A] <: OutputLike[A]](input: OL[T], name: String = "Softplus")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T], ev: Aux[OL, T]): OL[T]
  65. def softplusGradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
    Attributes
    protected
  66. def softplusHessian[T](op: Op[(Output[T], Output[T]), Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): (Output[T], Output[T])
    Attributes
    protected
  67. def softsign[T, OL[A] <: OutputLike[A]](input: OL[T], name: String = "Softsign")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T], ev: Aux[OL, T]): OL[T]
  68. def softsignGradient[T](op: Op[Output[T], Output[T]], outputGradient: Output[T])(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T]): Output[T]
    Attributes
    protected
  69. def sparseSoftmaxCrossEntropy[T, I](logits: Output[T], labels: Output[I], axis: Int = -1, name: String = "SparseSoftmaxCrossEntropy")(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T], arg2: core.types.TF[I], arg3: core.types.IsIntOrLong[I]): Output[T]
  70. def sparseSoftmaxCrossEntropyGradient[T, I](op: Op[(Output[T], Output[I]), (Output[T], Output[T])], outputGradient: (Output[T], Output[T]))(implicit arg0: core.types.TF[T], arg1: core.types.IsDecimal[T], arg2: core.types.TF[I], arg3: core.types.IsIntOrLong[I]): (Output[T], Output[I])
    Attributes
    protected
  71. final def synchronized[T0](arg0: ⇒ T0): T0
    Definition Classes
    AnyRef
  72. def toString(): String
    Definition Classes
    AnyRef → Any
  73. def topK[T](input: Output[T], k: Output[Int], sorted: Boolean = true, name: String = "TopK")(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): (Output[T], Output[Int])
  74. def topKGradient[T](op: Op[(Output[T], Output[Int]), (Output[T], Output[Int])], outputGradient: (Output[T], Output[Int]))(implicit arg0: core.types.TF[T], arg1: core.types.IsReal[T]): (Output[T], Output[Int])
    Attributes
    protected
  75. final def wait(): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  76. final def wait(arg0: Long, arg1: Int): Unit
    Definition Classes
    AnyRef
    Annotations
    @throws( ... )
  77. final def wait(arg0: Long): Unit
    Definition Classes
    AnyRef
    Annotations
    @native() @throws( ... )

Inherited from AnyRef

Inherited from Any

Ungrouped