skainet-lang-core/sk.ainet.lang.tensor.ops/VoidTensorOps

VoidTensorOps

class VoidTensorOps : TensorOps(source)

Constructors

VoidTensorOps

constructor()

Functions

abs

open override fun <T : DType, V> abs(tensor: Tensor<T, V>): Tensor<T, V>

Element-wise absolute value: |x|

add

open override fun <T : DType, V> add(a: Tensor<T, V>, b: Tensor<T, V>): Tensor<T, V>

addScalar

open override fun <T : DType, V> addScalar(a: Tensor<T, V>, b: Number): Tensor<T, V>

avgPool2d

open override fun <T : DType, V> avgPool2d(input: Tensor<T, V>, kernelSize: Pair<Int, Int>, stride: Pair<Int, Int>, padding: Pair<Int, Int>, countIncludePad: Boolean): Tensor<T, V>

clamp

open override fun <T : DType, V> clamp(tensor: Tensor<T, V>, minVal: Float, maxVal: Float): Tensor<T, V>

Element-wise clamp: min(max(x, minVal), maxVal)

concat

open override fun <T : DType, V> concat(tensors: List<Tensor<T, V>>, dim: Int): Tensor<T, V>

conv1d

open override fun <T : DType, V> conv1d(input: Tensor<T, V>, weight: Tensor<T, V>, bias: Tensor<T, V>?, stride: Int, padding: Int, dilation: Int, groups: Int): Tensor<T, V>

conv2d

open override fun <T : DType, V> conv2d(input: Tensor<T, V>, weight: Tensor<T, V>, bias: Tensor<T, V>?, stride: Pair<Int, Int>, padding: Pair<Int, Int>, dilation: Pair<Int, Int>, groups: Int): Tensor<T, V>

conv3d

open override fun <T : DType, V> conv3d(input: Tensor<T, V>, weight: Tensor<T, V>, bias: Tensor<T, V>?, stride: Triple<Int, Int, Int>, padding: Triple<Int, Int, Int>, dilation: Triple<Int, Int, Int>, groups: Int): Tensor<T, V>

convert

open override fun <TFrom : DType, TTo : DType, V> convert(tensor: Tensor<TFrom, V>, targetType: TTo): Tensor<TTo, V>

divide

open override fun <T : DType, V> divide(a: Tensor<T, V>, b: Tensor<T, V>): Tensor<T, V>

divScalar

open override fun <T : DType, V> divScalar(a: Tensor<T, V>, b: Number): Tensor<T, V>

elu

open override fun <T : DType, V> elu(tensor: Tensor<T, V>, alpha: Float): Tensor<T, V>

flatten

open override fun <T : DType, V> flatten(tensor: Tensor<T, V>, startDim: Int, endDim: Int): Tensor<T, V>

open override fun <T : DType, V> ge(tensor: Tensor<T, V>, value: Float): Tensor<T, V>

Element-wise greater than or equal: x >= value → 1.0, else 0.0

gelu

open override fun <T : DType, V> gelu(tensor: Tensor<T, V>): Tensor<T, V>

leakyRelu

open override fun <T : DType, V> leakyRelu(tensor: Tensor<T, V>, negativeSlope: Float): Tensor<T, V>

logSoftmax

open override fun <T : DType, V> logSoftmax(tensor: Tensor<T, V>, dim: Int): Tensor<T, V>

open override fun <T : DType, V> lt(tensor: Tensor<T, V>, value: Float): Tensor<T, V>

Element-wise less than: x < value → 1.0, else 0.0

matmul

open override fun <T : DType, V> matmul(a: Tensor<T, V>, b: Tensor<T, V>): Tensor<T, V>

maxPool2d

open override fun <T : DType, V> maxPool2d(input: Tensor<T, V>, kernelSize: Pair<Int, Int>, stride: Pair<Int, Int>, padding: Pair<Int, Int>): Tensor<T, V>

mean

open override fun <T : DType, V> mean(tensor: Tensor<T, V>, dim: Int?): Tensor<T, V>

mulScalar

open override fun <T : DType, V> mulScalar(a: Tensor<T, V>, b: Number): Tensor<T, V>

multiply

open override fun <T : DType, V> multiply(a: Tensor<T, V>, b: Tensor<T, V>): Tensor<T, V>

narrow

open override fun <T : DType, V> narrow(tensor: Tensor<T, V>, dim: Int, start: Int, length: Int): Tensor<T, V>

Extract a sub-tensor along dimension dim starting at start with the given length.

pad2d

open override fun <T : DType, V> pad2d(tensor: Tensor<T, V>, padLeft: Int, padRight: Int, padTop: Int, padBottom: Int): Tensor<T, V>

Zero-pad a 4D tensor N, C, H, W on the spatial dimensions.

rdivScalar

open override fun <T : DType, V> rdivScalar(a: Number, b: Tensor<T, V>): Tensor<T, V>

relu

open override fun <T : DType, V> relu(tensor: Tensor<T, V>): Tensor<T, V>

reshape

open override fun <T : DType, V> reshape(tensor: Tensor<T, V>, newShape: Shape): Tensor<T, V>

rsubScalar

open override fun <T : DType, V> rsubScalar(a: Number, b: Tensor<T, V>): Tensor<T, V>

sigmoid

open override fun <T : DType, V> sigmoid(tensor: Tensor<T, V>): Tensor<T, V>

sign

open override fun <T : DType, V> sign(tensor: Tensor<T, V>): Tensor<T, V>

Element-wise sign: -1 for negative, 0 for zero, +1 for positive. Non-differentiable.

silu

open override fun <T : DType, V> silu(tensor: Tensor<T, V>): Tensor<T, V>

softmax

open override fun <T : DType, V> softmax(tensor: Tensor<T, V>, dim: Int): Tensor<T, V>

split

open override fun <T : DType, V> split(tensor: Tensor<T, V>, splitSize: Int, dim: Int): List<Tensor<T, V>>

sqrt

open override fun <T : DType, V> sqrt(tensor: Tensor<T, V>): Tensor<T, V>

squeeze

open override fun <T : DType, V> squeeze(tensor: Tensor<T, V>, dim: Int?): Tensor<T, V>

subScalar

open override fun <T : DType, V> subScalar(a: Tensor<T, V>, b: Number): Tensor<T, V>

subtract

open override fun <T : DType, V> subtract(a: Tensor<T, V>, b: Tensor<T, V>): Tensor<T, V>

sum

open override fun <T : DType, V> sum(tensor: Tensor<T, V>, dim: Int?): Tensor<T, V>

transpose

open override fun <T : DType, V> transpose(tensor: Tensor<T, V>): Tensor<T, V>

tril

open override fun <T : DType, V> tril(tensor: Tensor<T, V>, k: Int): Tensor<T, V>

unfold

open override fun <T : DType, V> unfold(tensor: Tensor<T, V>, dim: Int, size: Int, step: Int): Tensor<T, V>

Extract sliding windows of size size along dimension dim with stride step. Result has one extra dimension appended containing the window elements.

unsqueeze

open override fun <T : DType, V> unsqueeze(tensor: Tensor<T, V>, dim: Int): Tensor<T, V>

upsample2d

open override fun <T : DType, V> upsample2d(input: Tensor<T, V>, scale: Pair<Int, Int>, mode: UpsampleMode, alignCorners: Boolean): Tensor<T, V>

variance

open override fun <T : DType, V> variance(tensor: Tensor<T, V>, dim: Int?): Tensor<T, V>