# Unary

The unary operator has a collection of basic unary calculation, like Absolute, trigonometric functions etc. An unary operator do element-wise calculation on each input tensor and store result in corresponding output tensor.

Few notes:

• The inputTensors and outputTensors should have same number of tensors.
• Corresponding input and output tensors should have same shapes.

All unary operators can be initialized:

let op = SomeUnaryOp()


## Trigonometric

#### SinOperator

For each input tensor x and output tensor y: $$y = sin(x)$$

#### SinhOperator

For each input tensor x and output tensor y: $$y = sinh(x)$$

#### TanOperator

For each input tensor x and output tensor y: $$y = tan(x)$$

#### TanhOperator

For each input tensor x and output tensor y: $$y = tanh(x)$$

#### CosOperator

For each input tensor x and output tensor y: $$y = cos(x)$$

#### CoshOperator

For each input tensor x and output tensor y: $$y = cosh(x)$$

#### ArcsinOperator

For each input tensor x and output tensor y: $$y = acsin(x)$$

#### ArcsinhOperator

For each input tensor x and output tensor y: $$y = acsinh(x)$$

#### ArccosOperator

For each input tensor x and output tensor y: $$y = arccos(x)$$

#### ArccosOperator

For each input tensor x and output tensor y: $$y = arccos(x)$$

#### ArccoshOperator

For each input tensor x and output tensor y: $$y = arctanh(x)$$

#### ArctanhOperator

For each input tensor x and output tensor y: $$y = arctanh(x)$$

#### DegreeOperator

Convert radians to degrees. For each input tensor x and output tensor y: $$y = x \times 180/ \pi$$

Convert degree to radian. For each input tensor x and output tensor y: $$y = x \times \pi / 180$$

## Round and abs

#### FloorOperator

For each input tensor x and output tensor y: $$y = floor(x)$$

#### CeilOperator

For each input tensor x and output tensor y: $$y = ceil(x)$$

#### RintOperator

Operator computes element-wise rounded value to the nearest integer of the input. For each input tensor x and output tensor y: $$y = rint(x)$$

#### RoundOperator

Operator computes element-wise rounded value to the truncating integers of input values. For each input tensor x and output tensor y: $$y = round(x)$$

#### AbsOperator

Compute element-wise abs values of input tensors. For each input tensor x and output tensor y: $$y =abs(x)$$

## Exponential, sqrt and logarithm

#### SquareOperator

For each input tensor x and output tensor y: $$y = x \times x$$

#### SqrtOperator

For each input tensor x and output tensor y: $$y = sqrt(x)$$

#### ExpOperator

For each input tensor x and output tensor y: $$y = e^{x}$$

#### Expm1Operator

For each input tensor x and output tensor y: $$y = e^{x} - 1$$

#### RsqrtOperator

For each input tensor x and output tensor y: $$y = 1 / sqrt(x)$$

#### LogOperator

For each input tensor x and output tensor y: $$y = log_{e}(x)$$

#### Log2Operator

For each input tensor x and output tensor y: $$y = log_{2}(x)$$

#### Log10Operator

For each input tensor x and output tensor y: $$y = log_{10}(x)$$

#### Log1pOperator

For each input tensor x and output tensor y: $$y = log_{e}(1+x)$$