Class Tensor

Hierarchy

TensorBase
- Tensor
  - Parameter

Index

Constructors

constructor

new Tensor(node): Tensor
Parameters
- node: GraphNodeOutputRef
Returns Tensor
Overrides TensorBase.constructor
- Defined in tensor.ts:105
new Tensor(spec): Tensor
Parameters
- spec: TensorSpec
Returns Tensor
Overrides TensorBase.constructor
- Defined in tensor.ts:106
new Tensor(array, dtype?, device?, requiresGrad?): Tensor
Parameters
- array: TensorData
- Optional dtype: Dtype
- Optional device: Deviceish
- Optional requiresGrad: boolean
Returns Tensor
Overrides TensorBase.constructor
- Defined in tensor.ts:107

Properties

`Private` _device

_device: Device

`Private` _dtype

_dtype: Dtype

`Private` _gradCtx

_gradCtx: null | GradientContext

`Private` _gradFunc

_gradFunc: null | GradientFunction

`Private` _node

_node: GraphNodeOutputRef

`Private` _requiresGrad

_requiresGrad: boolean = false

`Private` _shape

_shape: Shape

`Private` _strides

_strides: Strides

grad

grad: null | Tensor = null

Accessors

[toStringTag]

get [toStringTag](): string
Returns string
- Defined in tensor.ts:200

device

get device(): Device
Returns Device
- Defined in tensor.ts:68

dtype

get dtype(): Dtype
Returns Dtype
- Defined in tensor.ts:56

gradFunc

get gradFunc(): null | GradientFunction
Returns null | GradientFunction
- Defined in tensor.ts:101

isContiguous

get isContiguous(): boolean
Returns boolean
- Defined in tensor.ts:71

`Private` isScalar

get isScalar(): boolean
Returns boolean
- Defined in tensor.ts:83

ndim

get ndim(): number
Returns number
- Defined in tensor.ts:65

node

get node(): GraphNodeOutputRef
Returns GraphNodeOutputRef
- Defined in tensor.ts:49

requiresGrad

get requiresGrad(): boolean
Returns boolean
- Defined in tensor.ts:90
set requiresGrad(value): void
Parameters
- value: boolean
Returns void
- Defined in tensor.ts:93

shape

get shape(): Shape
Returns Shape
- Defined in tensor.ts:59

storage

get storage(): UntypedStorage
Returns UntypedStorage
- Defined in tensor.ts:52

strides

get strides(): Strides
Returns Strides
- Defined in tensor.ts:62

Methods

abs

abs(): Tensor

Plot of abs and its gradient

Calculates:

output = abs(input)

Gradient:

inputGrad = input == 0 ? 0 : (input > 0 ? outputGrad : -outputGrad)

Returns Tensor

the output tensor

abs_

abs_(): Tensor

Plot of abs and its gradient

Calculates:

output = abs(input)

Gradient:

inputGrad = input == 0 ? 0 : (input > 0 ? outputGrad : -outputGrad)

Returns Tensor

the output tensor

absolute

absolute(): Tensor

Alias for abs.

Plot of abs and its gradient

Calculates:

output = abs(input)

Gradient:

inputGrad = input == 0 ? 0 : (input > 0 ? outputGrad : -outputGrad)

Returns Tensor

the output tensor

acos

acos(): Tensor

Plot of acos and its gradient

Calculates:

output = acos(input)

Gradient:

inputGrad = -outputGrad / sqrt(1 - input * input)

Returns Tensor

the output tensor

acos_

acos_(): Tensor

Plot of acos and its gradient

Calculates:

output = acos(input)

Gradient:

inputGrad = -outputGrad / sqrt(1 - input * input)

Returns Tensor

the output tensor

acosh

acosh(): Tensor

Plot of acosh and its gradient

Calculates:

output = acosh(input)

Gradient:

inputGrad = outputGrad / sqrt(input * input - 1)

Returns Tensor

the output tensor

acosh_

acosh_(): Tensor

Plot of acosh and its gradient

Calculates:

output = acosh(input)

Gradient:

inputGrad = outputGrad / sqrt(input * input - 1)

Returns Tensor

the output tensor

add

add(other, alpha?): Tensor
Calculates:
```
output = input + other * alpha
```
Gradient:
```
inputGrad = outputGrad; otherGrad = outputGrad
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
- Optional alpha: number
  
  the alpha value to multiply other with
Returns Tensor
the output tensor
- Defined in tensor.ts:674

add_

add_(other, alpha?): Tensor
Calculates:
```
output = input + other * alpha
```
Gradient:
```
inputGrad = outputGrad; otherGrad = outputGrad
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
- Optional alpha: number
  
  the alpha value to multiply other with
Returns Tensor
the output tensor
- Defined in tensor.ts:692

all

all(dim?, keepdim?): Tensor
Calculates:
```
output = output && input
```
with an initial value of output = 1.

Gradient:
```
inputGrad = output ? outputGrad : 0.0
```
Parameters
- Optional dim: number | number[]
- Optional keepdim: boolean
Returns Tensor
the output tensor
- Defined in tensor.ts:3033

any

any(dim?, keepdim?): Tensor
Calculates:
```
output = output || input
```
with an initial value of output = 0.

Gradient:
```
inputGrad = output ? outputGrad : 0.0
```
Parameters
- Optional dim: number | number[]
- Optional keepdim: boolean
Returns Tensor
the output tensor
- Defined in tensor.ts:3051

arccos

arccos(): Tensor

Alias for acos.

Plot of acos and its gradient

Calculates:

output = acos(input)

Gradient:

inputGrad = -outputGrad / sqrt(1 - input * input)

Returns Tensor

the output tensor

arccosh

arccosh(): Tensor

Alias for acosh.

Plot of acosh and its gradient

Calculates:

output = acosh(input)

Gradient:

inputGrad = outputGrad / sqrt(input * input - 1)

Returns Tensor

the output tensor

arcsin

arcsin(): Tensor

Alias for asin.

Plot of asin and its gradient

Calculates:

output = asin(input)

Gradient:

inputGrad = outputGrad / sqrt(1 - input * input)

Returns Tensor

the output tensor

arcsinh

arcsinh(): Tensor

Alias for asinh.

Plot of asinh and its gradient

Calculates:

output = asinh(input)

Gradient:

inputGrad = outputGrad / sqrt(input * input + 1)

Returns Tensor

the output tensor

arctan

arctan(): Tensor
Alias for atan.

Calculates:
```
output = atan(input)
```
Gradient:
```
inputGrad = outputGrad / (input * input + 1)
```
Returns Tensor
the output tensor
- Defined in tensor.ts:887

arctan2

arctan2(other): Tensor

Alias for atan2.

Calculates:

output = atan2(input, other)

Gradient:

inputGrad = outputGrad * other / (input * input + other * other); otherGrad = -outputGrad * input / (input * input + other * other)

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

asin

asin(): Tensor

Plot of asin and its gradient

Calculates:

output = asin(input)

Gradient:

inputGrad = outputGrad / sqrt(1 - input * input)

Returns Tensor

the output tensor

asin_

asin_(): Tensor

Plot of asin and its gradient

Calculates:

output = asin(input)

Gradient:

inputGrad = outputGrad / sqrt(1 - input * input)

Returns Tensor

the output tensor

asinh

asinh(): Tensor

Plot of asinh and its gradient

Calculates:

output = asinh(input)

Gradient:

inputGrad = outputGrad / sqrt(input * input + 1)

Returns Tensor

the output tensor

asinh_

asinh_(): Tensor

Plot of asinh and its gradient

Calculates:

output = asinh(input)

Gradient:

inputGrad = outputGrad / sqrt(input * input + 1)

Returns Tensor

the output tensor

atan

atan(): Tensor

Plot of atan and its gradient

Calculates:

output = atan(input)

Gradient:

inputGrad = outputGrad / (input * input + 1)

Returns Tensor

the output tensor

atan2

atan2(other): Tensor

Calculates:

output = atan2(input, other)

Gradient:

inputGrad = outputGrad * other / (input * input + other * other); otherGrad = -outputGrad * input / (input * input + other * other)

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

atan2_

atan2_(other): Tensor

Calculates:

output = atan2(input, other)

Gradient:

inputGrad = outputGrad * other / (input * input + other * other); otherGrad = -outputGrad * input / (input * input + other * other)

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

atan_

atan_(): Tensor

Plot of atan and its gradient

Calculates:

output = atan(input)

Gradient:

inputGrad = outputGrad / (input * input + 1)

Returns Tensor

the output tensor

backward

backward(gradient?): void
Parameters
- Optional gradient: Tensor
Returns void
- Defined in tensor.ts:370

ceil

ceil(): Tensor
Calculates:
```
output = ceil(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1015

ceil_

ceil_(): Tensor
Calculates:
```
output = ceil(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1033

copysign

copysign(other): Tensor

Calculates:

output = other >= 0 ? abs(input) : -abs(input)

Gradient:

var dir = other >= 0 ? (input >= 0 ? 1.0 : -1.0) : (input >= 0 ? -1.0 : 1.0); inputGrad = input == 0.0 ? 0.0 : outputGrad * dir; otherGrad = 0

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

copysign_

copysign_(other): Tensor

Calculates:

output = other >= 0 ? abs(input) : -abs(input)

Gradient:

var dir = other >= 0 ? (input >= 0 ? 1.0 : -1.0) : (input >= 0 ? -1.0 : 1.0); inputGrad = input == 0.0 ? 0.0 : outputGrad * dir; otherGrad = 0

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

cos

cos(): Tensor
Calculates:
```
output = cos(input)
```
Gradient:
```
inputGrad = -outputGrad * sin(input)
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1124

cos_

cos_(): Tensor
Calculates:
```
output = cos(input)
```
Gradient:
```
inputGrad = -outputGrad * sin(input)
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1142

cosh

cosh(): Tensor

Plot of cosh and its gradient

Calculates:

output = cosh(input)

Gradient:

inputGrad = outputGrad * sinh(input)

Returns Tensor

the output tensor

cosh_

cosh_(): Tensor

Plot of cosh and its gradient

Calculates:

output = cosh(input)

Gradient:

inputGrad = outputGrad * sinh(input)

Returns Tensor

the output tensor

countNonzero

countNonzero(dim?, keepdim?): Tensor
Calculates:
```
output = output + (input != 0)
```
with an initial value of output = 0.0.
Parameters
- Optional dim: number | number[]
- Optional keepdim: boolean
Returns Tensor
the output tensor
- Defined in tensor.ts:3136

deg2rad

deg2rad(): Tensor

Plot of deg2rad and its gradient

Calculates:

output = input * 0.017453292519943295

Gradient:

inputGrad = outputGrad * 0.017453292519943295

Returns Tensor

the output tensor

deg2rad_

deg2rad_(): Tensor

Plot of deg2rad and its gradient

Calculates:

output = input * 0.017453292519943295

Gradient:

inputGrad = outputGrad * 0.017453292519943295

Returns Tensor

the output tensor

detach

detach(): Tensor
Returns Tensor
- Defined in tensor.ts:347

div

div(other): Tensor
Calculates:
```
output = input / other
```
Gradient:
```
inputGrad = outputGrad / other; otherGrad = -outputGrad * input / (other * other)
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
Returns Tensor
the output tensor
- Defined in tensor.ts:1240

div_

div_(other): Tensor
Calculates:
```
output = input / other
```
Gradient:
```
inputGrad = outputGrad / other; otherGrad = -outputGrad * input / (other * other)
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
Returns Tensor
the output tensor
- Defined in tensor.ts:1276

divide

divide(other): Tensor
Alias for div.

Calculates:
```
output = input / other
```
Gradient:
```
inputGrad = outputGrad / other; otherGrad = -outputGrad * input / (other * other)
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
Returns Tensor
the output tensor
- Defined in tensor.ts:1259

eager

eager(): Tensor
Eagerly compute this tensor if it is lazy.

Returns Tensor
This tensor.
- Defined in tensor.ts:218

exp

exp(): Tensor
Calculates:
```
output = exp(input)
```
Gradient:
```
inputGrad = outputGrad * exp(input)
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1330

exp2

exp2(): Tensor

Plot of exp2 and its gradient

Calculates:

output = exp2(input)

Gradient:

inputGrad = outputGrad * exp2(input) * 0.6931471805599453

Returns Tensor

the output tensor

exp2_

exp2_(): Tensor

Plot of exp2 and its gradient

Calculates:

output = exp2(input)

Gradient:

inputGrad = outputGrad * exp2(input) * 0.6931471805599453

Returns Tensor

the output tensor

exp_

exp_(): Tensor
Calculates:
```
output = exp(input)
```
Gradient:
```
inputGrad = outputGrad * exp(input)
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1348

expand

expand(shape): Tensor
Parameters
- shape: Shape
Returns Tensor
- Defined in tensor.ts:411

expm1

expm1(): Tensor

Plot of expm1 and its gradient

Calculates:

output = exp(input) - 1.0

Gradient:

inputGrad = outputGrad * exp(input)

Returns Tensor

the output tensor

expm1_

expm1_(): Tensor

Plot of expm1 and its gradient

Calculates:

output = exp(input) - 1.0

Gradient:

inputGrad = outputGrad * exp(input)

Returns Tensor

the output tensor

fix

fix(): Tensor
Alias for trunc.

Calculates:
```
output = trunc(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2924

flatten

flatten(startDim?, endDim?): Tensor
Parameters
- startDim: number = 0
- endDim: number = -1
Returns Tensor
- Defined in tensor.ts:434

floor

floor(): Tensor
Calculates:
```
output = floor(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1447

floor_

floor_(): Tensor
Calculates:
```
output = floor(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1465

frac

frac(): Tensor

$Plot of frac and its gradient$

Calculates:

output = input >= 0.0 ? fract(input) : -fract(-input)

Gradient:

inputGrad = outputGrad

Returns Tensor

the output tensor

frac_

frac_(): Tensor

$Plot of frac and its gradient$

Calculates:

output = input >= 0.0 ? fract(input) : -fract(-input)

Gradient:

inputGrad = outputGrad

Returns Tensor

the output tensor

gather

gather(dim, index): Tensor
Gathers values along an axis specified by dim.
Parameters
- dim: number
- index: Tensor
Returns Tensor
- Defined in tensor.ts:438

hypot

hypot(other): Tensor

Calculates:

output = sqrt(input * input + other * other)

Gradient:

inputGrad = outputGrad * input / sqrt(input * input + other * other); otherGrad = outputGrad * other / sqrt(input * input + other * other)

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

hypot_

hypot_(other): Tensor

Calculates:

output = sqrt(input * input + other * other)

Gradient:

inputGrad = outputGrad * input / sqrt(input * input + other * other); otherGrad = outputGrad * other / sqrt(input * input + other * other)

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

ldexp

ldexp(other): Tensor

Calculates:

output = input * pow(2.0, other)

Gradient:

var out = pow(2.0, other); inputGrad = outputGrad * out; otherGrad = outputGrad * input * out * 0.6931471805599453

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

ldexp_

ldexp_(other): Tensor

Calculates:

output = input * pow(2.0, other)

Gradient:

var out = pow(2.0, other); inputGrad = outputGrad * out; otherGrad = outputGrad * input * out * 0.6931471805599453

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

log

log(): Tensor
Calculates:
```
output = log(input)
```
Gradient:
```
inputGrad = outputGrad / input
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1665

log10

log10(): Tensor

Plot of log10 and its gradient

Calculates:

output = log(input) * 0.4342944819032518

Gradient:

inputGrad = outputGrad / (input * 2.302585092994046)

Returns Tensor

the output tensor

log10_

log10_(): Tensor

Plot of log10 and its gradient

Calculates:

output = log(input) * 0.4342944819032518

Gradient:

inputGrad = outputGrad / (input * 2.302585092994046)

Returns Tensor

the output tensor

log1p

log1p(): Tensor

Plot of log1p and its gradient

Calculates:

output = log(input + 1.0)

Gradient:

inputGrad = outputGrad / (input + 1.0)

Returns Tensor

the output tensor

log1p_

log1p_(): Tensor

Plot of log1p and its gradient

Calculates:

output = log(input + 1.0)

Gradient:

inputGrad = outputGrad / (input + 1.0)

Returns Tensor

the output tensor

log2

log2(): Tensor

Plot of log2 and its gradient

Calculates:

output = log2(input)

Gradient:

inputGrad = outputGrad / (input * 0.6931471805599453)

Returns Tensor

the output tensor

log2_

log2_(): Tensor

Plot of log2 and its gradient

Calculates:

output = log2(input)

Gradient:

inputGrad = outputGrad / (input * 0.6931471805599453)

Returns Tensor

the output tensor

log_

log_(): Tensor
Calculates:
```
output = log(input)
```
Gradient:
```
inputGrad = outputGrad / input
```
Returns Tensor
the output tensor
- Defined in tensor.ts:1683

logaddexp

logaddexp(other): Tensor

Calculates:

output = log(exp(input) + exp(other))

Gradient:

var ein = exp(input); var eoth = exp(other); var addeinv = outputGrad/(ein + eoth); inputGrad = addeinv * ein; otherGrad = addeinv * eoth

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

logaddexp2

logaddexp2(other): Tensor

Calculates:

output = log2(exp2(input) + exp2(other))

Gradient:

var ein = exp2(input); var eoth = exp2(other); var sum_ein_eoth = ein + eoth; inputGrad = outputGrad * (ein / sum_ein_eoth); otherGrad = outputGrad * (eoth / sum_ein_eoth );

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

logaddexp2_

logaddexp2_(other): Tensor

Calculates:

output = log2(exp2(input) + exp2(other))

Gradient:

var ein = exp2(input); var eoth = exp2(other); var sum_ein_eoth = ein + eoth; inputGrad = outputGrad * (ein / sum_ein_eoth); otherGrad = outputGrad * (eoth / sum_ein_eoth );

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

logaddexp_

logaddexp_(other): Tensor

Calculates:

output = log(exp(input) + exp(other))

Gradient:

var ein = exp(input); var eoth = exp(other); var addeinv = outputGrad/(ein + eoth); inputGrad = addeinv * ein; otherGrad = addeinv * eoth

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

mean

mean(dim?, keepdim?): Tensor
Calculates:
```
output = output + input
```
with an initial value of output = 0.0.

Gradient:
```
inputGrad = outputGrad / f32(inputSize)
```
Parameters
- Optional dim: number | number[]
- Optional keepdim: boolean
Returns Tensor
the output tensor
- Defined in tensor.ts:3069

mm

mm(other): Tensor
Parameters
- other: Tensor
Returns Tensor
- Defined in tensor.ts:441

mul

mul(other): Tensor
Calculates:
```
output = input * other
```
Gradient:
```
inputGrad = outputGrad * other; otherGrad = outputGrad * input
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
Returns Tensor
the output tensor
- Defined in tensor.ts:1960

mul_

mul_(other): Tensor
Calculates:
```
output = input * other
```
Gradient:
```
inputGrad = outputGrad * other; otherGrad = outputGrad * input
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
Returns Tensor
the output tensor
- Defined in tensor.ts:1996

multiply

multiply(other): Tensor
Alias for mul.

Calculates:
```
output = input * other
```
Gradient:
```
inputGrad = outputGrad * other; otherGrad = outputGrad * input
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
Returns Tensor
the output tensor
- Defined in tensor.ts:1979

neg

neg(): Tensor
Calculates:
```
output = -input
```
Gradient:
```
inputGrad = -outputGrad
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2050

neg_

neg_(): Tensor
Calculates:
```
output = -input
```
Gradient:
```
inputGrad = -outputGrad
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2088

negative

negative(): Tensor
Alias for neg.

Calculates:
```
output = -input
```
Gradient:
```
inputGrad = -outputGrad
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2070

norm

norm(dim?, keepdim?): Tensor
Calculates:
```
output = output + input * input
```
with an initial value of output = 0.0.

Gradient:
```
inputGrad = outputGrad * input / output
```
Parameters
- Optional dim: number | number[]
- Optional keepdim: boolean
Returns Tensor
the output tensor
- Defined in tensor.ts:3087

numel

numel(): number
Returns number
- Defined in tensor.ts:444

positive

positive(): Tensor
Calculates:
```
output = input
```
Gradient:
```
inputGrad = outputGrad
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2109

positive_

positive_(): Tensor
Calculates:
```
output = input
```
Gradient:
```
inputGrad = outputGrad
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2127

pow

pow(other): Tensor

Calculates:

output = input >= 0 || fract(other) != 0 ? pow(input, other) :
        pow(-input, other) * ((i32(other) & 1) != 0 ? -1f : 1f)

Gradient:

inputGrad = input >= 0 || fract(other) != 0 ? outputGrad * other * pow(input, other - 1.0) :
        outputGrad * other * pow(-input, other - 1) * ((i32(other - 1) & 1) != 0 ? -1f : 1f);
    otherGrad = outputGrad * pow(input, other) * log(input)

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

pow_

pow_(other): Tensor

Calculates:

output = input >= 0 || fract(other) != 0 ? pow(input, other) :
        pow(-input, other) * ((i32(other) & 1) != 0 ? -1f : 1f)

Gradient:

inputGrad = input >= 0 || fract(other) != 0 ? outputGrad * other * pow(input, other - 1.0) :
        outputGrad * other * pow(-input, other - 1) * ((i32(other - 1) & 1) != 0 ? -1f : 1f);
    otherGrad = outputGrad * pow(input, other) * log(input)

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

prod

prod(dim?, keepdim?): Tensor
Calculates:
```
output = output * input
```
with an initial value of output = 1.0.

Gradient:
```
inputGrad = outputGrad * output / input
```
Parameters
- Optional dim: number | number[]
- Optional keepdim: boolean
Returns Tensor
the output tensor
- Defined in tensor.ts:3105

rad2deg

rad2deg(): Tensor

Plot of rad2deg and its gradient

Calculates:

output = input * 57.29577951308232

Gradient:

inputGrad = outputGrad * 57.29577951308232

Returns Tensor

the output tensor

rad2deg_

rad2deg_(): Tensor

Plot of rad2deg and its gradient

Calculates:

output = input * 57.29577951308232

Gradient:

inputGrad = outputGrad * 57.29577951308232

Returns Tensor

the output tensor

reciprocal

reciprocal(): Tensor

Plot of reciprocal and its gradient

Calculates:

output = 1.0 / input

Gradient:

inputGrad = -outputGrad / (input * input)

Returns Tensor

the output tensor

reciprocal_

reciprocal_(): Tensor

Plot of reciprocal and its gradient

Calculates:

output = 1.0 / input

Gradient:

inputGrad = -outputGrad / (input * input)

Returns Tensor

the output tensor

relu

relu(): Tensor

Plot of relu and its gradient

Calculates:

output = max(input, 0.0)

Gradient:

inputGrad = input > 0.0 ? outputGrad : 0.0

Returns Tensor

the output tensor

relu_

relu_(): Tensor

Plot of relu and its gradient

Calculates:

output = max(input, 0.0)

Gradient:

inputGrad = input > 0.0 ? outputGrad : 0.0

Returns Tensor

the output tensor

reshape

reshape(shape): Tensor
Parameters
- shape: Shape
Returns Tensor
- Defined in tensor.ts:447

reshapeAs

reshapeAs(other): Tensor
Parameters
- other: Tensor
Returns Tensor
- Defined in tensor.ts:450

round

round(): Tensor
Calculates:
```
output = round(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2341

round_

round_(): Tensor
Calculates:
```
output = round(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2359

rsqrt

rsqrt(): Tensor

Plot of rsqrt and its gradient

Calculates:

output = 1.0 / sqrt(input)

Gradient:

inputGrad = -outputGrad / (2.0 * sqrt(input) * input)

Returns Tensor

the output tensor

rsqrt_

rsqrt_(): Tensor

Plot of rsqrt and its gradient

Calculates:

output = 1.0 / sqrt(input)

Gradient:

inputGrad = -outputGrad / (2.0 * sqrt(input) * input)

Returns Tensor

the output tensor

runKernel

runKernel(name, config, params, outputs, ...additionalInputs): Tensor[]
Parameters
- name: string
- config: KernelConfigInput
- params: KernelParamsInput
- outputs: Tensor[] | Shape[]
- Rest ...additionalInputs: Tensor[]
Returns Tensor[]
- Defined in tensor.ts:278

runKernelInplace

runKernelInplace(name, config, params, ...additionalInputs): Tensor
Parameters
- name: string
- config: KernelConfigInput
- params: KernelParamsInput
- Rest ...additionalInputs: Tensor[]
Returns Tensor
- Defined in tensor.ts:248

setGradientFunction

setGradientFunction(ctx, gradFunc): void
Parameters
- ctx: GradientContext
- gradFunc: GradientFunction
Returns void
- Defined in tensor.ts:361

sigmoid

sigmoid(): Tensor

Plot of sigmoid and its gradient

Calculates:

output = 1.0 / (1.0 + exp(-input))

Gradient:

var out = 1.0 / (1.0 + exp(-input)); inputGrad = outputGrad * out * (1.0 - out)

Returns Tensor

the output tensor

sigmoid_

sigmoid_(): Tensor

Plot of sigmoid and its gradient

Calculates:

output = 1.0 / (1.0 + exp(-input))

Gradient:

var out = 1.0 / (1.0 + exp(-input)); inputGrad = outputGrad * out * (1.0 - out)

Returns Tensor

the output tensor

sign

sign(): Tensor
Calculates:
```
output = sign(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2458

sign_

sign_(): Tensor
Calculates:
```
output = sign(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2476

silu

silu(): Tensor

Plot of silu and its gradient

Calculates:

output = input / (1.0 + exp(-input))

Gradient:

var out = 1.0 / (1.0 + exp(-input)); inputGrad = outputGrad * (out + input * out * (1.0 - out))

Returns Tensor

the output tensor

silu_

silu_(): Tensor

Plot of silu and its gradient

Calculates:

output = input / (1.0 + exp(-input))

Gradient:

var out = 1.0 / (1.0 + exp(-input)); inputGrad = outputGrad * (out + input * out * (1.0 - out))

Returns Tensor

the output tensor

sin

sin(): Tensor
Calculates:
```
output = sin(input)
```
Gradient:
```
inputGrad = outputGrad * cos(input)
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2536

sin_

sin_(): Tensor
Calculates:
```
output = sin(input)
```
Gradient:
```
inputGrad = outputGrad * cos(input)
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2554

sinc

sinc(): Tensor

Plot of sinc and its gradient

Calculates:

var inpi = input * 3.141592653589793; output = input == 0.0 ? 1.0 : sin(inpi) / inpi

Gradient:

var inpi = input * 3.141592653589793; inputGrad = input == 0.0 ? 0.0 : (outputGrad * 3.141592653589793 * (inpi*cos(inpi) - sin(inpi)) / (inpi*inpi))

Returns Tensor

the output tensor

sinc_

sinc_(): Tensor

Plot of sinc and its gradient

Calculates:

var inpi = input * 3.141592653589793; output = input == 0.0 ? 1.0 : sin(inpi) / inpi

Gradient:

var inpi = input * 3.141592653589793; inputGrad = input == 0.0 ? 0.0 : (outputGrad * 3.141592653589793 * (inpi*cos(inpi) - sin(inpi)) / (inpi*inpi))

Returns Tensor

the output tensor

sinh

sinh(): Tensor

Plot of sinh and its gradient

Calculates:

output = sinh(input)

Gradient:

inputGrad = outputGrad * cosh(input)

Returns Tensor

the output tensor

sinh_

sinh_(): Tensor

Plot of sinh and its gradient

Calculates:

output = sinh(input)

Gradient:

inputGrad = outputGrad * cosh(input)

Returns Tensor

the output tensor

sqrt

sqrt(): Tensor

Plot of sqrt and its gradient

Calculates:

output = sqrt(input)

Gradient:

inputGrad = outputGrad / (2.0 * sqrt(input))

Returns Tensor

the output tensor

sqrt_

sqrt_(): Tensor

Plot of sqrt and its gradient

Calculates:

output = sqrt(input)

Gradient:

inputGrad = outputGrad / (2.0 * sqrt(input))

Returns Tensor

the output tensor

square

square(): Tensor

Plot of square and its gradient

Calculates:

output = input * input

Gradient:

inputGrad = outputGrad * 2.0 * input

Returns Tensor

the output tensor

square_

square_(): Tensor

Plot of square and its gradient

Calculates:

output = input * input

Gradient:

inputGrad = outputGrad * 2.0 * input

Returns Tensor

the output tensor

squeeze

squeeze(dim?): Tensor
Parameters
- Optional dim: number | number[]
Returns Tensor
- Defined in tensor.ts:453

sub

sub(other, alpha?): Tensor
Calculates:
```
output = input - other * alpha
```
Gradient:
```
inputGrad = outputGrad; otherGrad = -outputGrad
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
- Optional alpha: number
  
  the alpha value to multiply other with
Returns Tensor
the output tensor
- Defined in tensor.ts:2731

sub_

sub_(other, alpha?): Tensor
Calculates:
```
output = input - other * alpha
```
Gradient:
```
inputGrad = outputGrad; otherGrad = -outputGrad
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
- Optional alpha: number
  
  the alpha value to multiply other with
Returns Tensor
the output tensor
- Defined in tensor.ts:2769

subtract

subtract(other, alpha?): Tensor
Alias for sub.

Calculates:
```
output = input - other * alpha
```
Gradient:
```
inputGrad = outputGrad; otherGrad = -outputGrad
```
Parameters
- other: number | Tensor
  
  the other tensor whose shape is broadcastable with the input tensor
- Optional alpha: number
  
  the alpha value to multiply other with
Returns Tensor
the output tensor
- Defined in tensor.ts:2751

sum

sum(dim?, keepdim?): Tensor
Calculates:
```
output = output + input
```
with an initial value of output = 0.0.

Gradient:
```
inputGrad = outputGrad
```
Parameters
- Optional dim: number | number[]
- Optional keepdim: boolean
Returns Tensor
the output tensor
- Defined in tensor.ts:3123

t

t(): Tensor
Returns Tensor
- Defined in tensor.ts:456

tan

tan(): Tensor

Plot of tan and its gradient

Calculates:

output = tan(input)

Gradient:

inputGrad = outputGrad / (cos(input) * cos(input))

Returns Tensor

the output tensor

tan_

tan_(): Tensor

Plot of tan and its gradient

Calculates:

output = tan(input)

Gradient:

inputGrad = outputGrad / (cos(input) * cos(input))

Returns Tensor

the output tensor

tanh

tanh(): Tensor

Plot of tanh and its gradient

Calculates:

output = tanh(input)

Gradient:

inputGrad = outputGrad * (1.0 - tanh(input) * tanh(input))

Returns Tensor

the output tensor

tanh_

tanh_(): Tensor

Plot of tanh and its gradient

Calculates:

output = tanh(input)

Gradient:

inputGrad = outputGrad * (1.0 - tanh(input) * tanh(input))

Returns Tensor

the output tensor

toArrayAsync

toArrayAsync(): Promise<number | TensorArrayData>
Returns Promise<number | TensorArrayData>
- Defined in tensor.ts:210

toString

toString(): string
Returns string
- Defined in tensor.ts:203

trunc

trunc(): Tensor
Calculates:
```
output = trunc(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2904

trunc_

trunc_(): Tensor
Calculates:
```
output = trunc(input)
```
Gradient:
```
inputGrad = 0
```
Returns Tensor
the output tensor
- Defined in tensor.ts:2942

uniform_

uniform_(lowerBound, upperBound): Tensor
Parameters
- lowerBound: number
- upperBound: number
Returns Tensor
- Defined in tensor.ts:459

unsqueeze

unsqueeze(dim?): Tensor
Parameters
- Optional dim: number
Returns Tensor
- Defined in tensor.ts:468

view

view(shape): Tensor
Parameters
- shape: Shape
Returns Tensor
- Defined in tensor.ts:471

viewAs

viewAs(other): Tensor
Parameters
- other: Tensor
Returns Tensor
- Defined in tensor.ts:474

withShape

withShape(shape, strides): Tensor
Parameters
- shape: Shape
- strides: Strides
Returns Tensor
- Defined in tensor.ts:223

xlogy

xlogy(other): Tensor

Calculates:

output = input == 0.0 ? 0.0 : input * log(other)

Gradient:

inputGrad = input == 0.0 ? 0.0 : outputGrad * log(other); otherGrad = input == 0.0 ? 0.0 : outputGrad * (input / other);

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

xlogy_

xlogy_(other): Tensor

Calculates:

output = input == 0.0 ? 0.0 : input * log(other)

Gradient:

inputGrad = input == 0.0 ? 0.0 : outputGrad * log(other); otherGrad = input == 0.0 ? 0.0 : outputGrad * (input / other);

Parameters

other: number | Tensor

the other tensor whose shape is broadcastable with the input tensor

Returns Tensor

the output tensor

zero_

zero_(): Tensor
Returns Tensor
- Defined in tensor.ts:477

Class Tensor

Hierarchy

Index

Constructors

Properties

Accessors

Methods

Constructors

constructor

Parameters

node: GraphNodeOutputRef

Returns Tensor

Parameters

spec: TensorSpec

Returns Tensor

Parameters

array: TensorData

Optional dtype: Dtype

Optional device: Deviceish

Optional requiresGrad: boolean

Returns Tensor

Properties

Private _device

Private _dtype

Private _gradCtx

Private _gradFunc

Private _node

Private _requiresGrad

Private _shape

Private _strides

grad

Accessors

[toStringTag]

Returns string

device

Returns Device

dtype

Returns Dtype

gradFunc

Returns null | GradientFunction

isContiguous

Returns boolean

Private isScalar

Returns boolean

ndim

Returns number

node

Returns GraphNodeOutputRef

requiresGrad

Returns boolean

Parameters

value: boolean

Returns void

shape

Returns Shape

storage

Returns UntypedStorage

strides

Returns Strides

Methods

abs

Returns Tensor

abs_

Returns Tensor

absolute

Returns Tensor

acos

Returns Tensor

acos_

Returns Tensor

acosh

Returns Tensor

acosh_

Returns Tensor

add

Parameters

other: number | Tensor

Optional alpha: number

Returns Tensor

add_

`Optional` dtype: Dtype

`Optional` device: Deviceish

`Optional` requiresGrad: boolean

`Private` _device

`Private` _dtype

`Private` _gradCtx

`Private` _gradFunc

`Private` _node

`Private` _requiresGrad

`Private` _shape

`Private` _strides

`Private` isScalar

`Optional` alpha: number

`Optional` alpha: number

`Optional` dim: number | number[]

`Optional` keepdim: boolean

`Optional` dim: number | number[]

`Optional` keepdim: boolean

`Optional` gradient: Tensor