# Package org.nd4j.linalg.api.ops.impl.transforms

• Class Summary
Class Description
Abs
Abs elementwise function
ACos
Log elementwise function
ACosh
ACosh elementwise function
And
Boolean AND pairwise transform
ASin
Arcsin elementwise function
ASinh
Arcsin elementwise function
Assign
Assign op: x = y, with broadcast as required
ATan
Arc Tangent elementwise function
ATan2
Arc Tangent elementwise function
ATanh
tan elementwise function
BaseDynamicTransformOp
BatchToSpace
N-dimensional batch to space operation.
BinaryMinimalRelativeError
BinaryRelativeError
Ceil
Ceiling elementwise function
Constant
Cos
Cosine elementwise function
Cosh
Cosine Hyperbolic elementwise function
Cube
Cube (x^3) elementwise function
Dilation2D
Dilation2D op wrapper
DynamicPartition
Transforms a given input tensor into numPartitions partitions, as indicated by the indices in "partitions".
DynamicStitch
Transforms a given input tensor into numPartitions partitions, as indicated by the indices in "partitions".
ELU
ELU: Exponential Linear Unit (alpha=1.0)
Introduced in paper:
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
Djork-ArnĂ© Clevert, Thomas Unterthiner, Sepp Hochreiter (2015)
http://arxiv.org/abs/1511.07289
Erf
Gaussian error function (erf) function, which is defined as
Erfc
Complementary Gaussian error function (erfc), defined as
Exp
Element-wise exponential function
Expm1
Element-wise exponential function minus 1, i.e.
Fill
Fill an array of given "shape" with the provided "value", e.g.
Floor
Floor elementwise function
HardSigmoid
HardSigmoid function
HardTanh
Hard tanh elementwise function
Histogram
Identity
Identity function
InvertPermutation
Inverse of index permutation.
IsFinite
IsFinite function
IsInf
IsInf function
IsMax
[1, 2, 3, 1] -> [0, 0, 1, 0]
IsNaN
IsNaN function
LeakyReLU
Leaky Rectified linear unit.
LegacyDropOut
DropOut implementation as Op PLEASE NOTE: This is legacy DropOut implementation, please consider using op with the same opName from randomOps
LegacyDropOutInverted
Inverted DropOut implementation as Op PLEASE NOTE: This is legacy DropOutInverted implementation, please consider using op with the same opName from randomOps
Log
Log elementwise function
Log1p
Log1p function
LogSigmoid
LogSigmoid function
LogSigmoidDerivative
LogSigmoid derivative
LogSoftMax
Log(softmax(X))
LogX
Log on arbitrary base op
MatchConditionTransform
Absolute sum the components
MatrixDeterminant
Matrix Determinant op Given input with shape [..., N, N] output the determinant for each sub-matrix.
MatrixDiag
MatrixDiagPart
MatrixInverse
Matrix Inverse Function
MatrixSetDiag
MaxOut
Max out activation: http://arxiv.org/pdf/1302.4389.pdf
Negative
Negative function
Not
Boolean AND pairwise transform
OldAtan2Op
atan2 operation
OldIdentity
Identity function
OldReverse
OldReverse op
OldSoftMax
Soft max function row_maxes is a row vector (max for each row) row_maxes = rowmaxes(input) diff = exp(input - max) / diff.rowSums() Outputs a probability distribution.
OneMinus
1 - input
Or
Boolean OR pairwise transform
ParallelConcat
Pow
Pow function
PowDerivative
Pow derivative z = n * x ^ (n-1)
RationalTanh
Rational Tanh Approximation elementwise function, as described at https://github.com/deeplearning4j/libnd4j/issues/351
Reciprocal
Created by susaneraly on 3/28/18.
RectifedLinear
Rectified linear units
RectifiedTanh
RectifiedTanh Essentially max(0, tanh(x))
RelativeError
Relu6
Rectified linear unit 6, i.e.
ReluLayer
Composed op: relu((X, W) + b)
ReplaceNans
Element-wise "Replace NaN" implementation as Op
Reverse
ReverseSequence
Created by farizrahman4u on 3/16/18.
ReverseV2
This is compatibility op for ReverseV2
Rint
Rint function
Round
Rounding function
RSqrt
RSqrt function
SELU
SELU activation function
Set
Set
SetRange
Set range to a particular set of values
Sigmoid
Sigmoid function
SigmoidDerivative
Sigmoid derivative
Sign
Signum function
Sin
Log elementwise function
Sinh
Sinh function
SoftMax
Soft max function row_maxes is a row vector (max for each row) row_maxes = rowmaxes(input) diff = exp(input - max) / diff.rowSums() Outputs a probability distribution.
SoftMaxDerivative
Softmax derivative
SoftPlus
SoftSign
Softsign element-wise activation function.
SpaceToBatch
N-dimensional space to batch operation.
Sqrt
Sqrt function
Square
Square function (x ^ 2)
Stabilize
Stabilization function, forces values to be within a range
Step
Unit step function.
Swish
Swish function
SwishDerivative
Swish derivative
Tan
Tanh elementwise function
TanDerivative
Tan Derivative elementwise function
Tanh
Tanh elementwise function
TanhDerivative
Tanh derivative
TimesOneMinus
If x is input: output is x*(1-x)
Trace
Matrix trace operation
Xor
Boolean XOR pairwise transform
XwPlusB
Composed op: mmul (X, W) + b