ITransform

Image transform that maps a tensor to a tensor.

Instance members

Name	Description
`this.apply arg1`

Compose

Compose multiple transforms into a single pipeline.

Function	Description
`apply transforms x`	Apply transforms sequentially.

apply

apply transforms x

Apply transforms sequentially.

Parameters

transforms : ITransform list
x : Tensor

Returns Tensor

Normalize

Channel-wise normalization: $(x - \mu) / \sigma$ . Input: $[C, H, W]$ or $[B, C, H, W]$ .

Record fields

Name	Description
`Mean`
`Std`

Instance members

Name	Description
`this.apply x`

Normalize module

Function	Description
`imageNet`	ImageNet normalization preset.

imageNet

imageNet

ImageNet normalization preset.

Returns Normalize

Resize

Resize to the target spatial size using bilinear interpolation. Input: $[C, H, W]$ or $[B, C, H, W]$ .

Record fields

Name	Description
`Height`
`Width`

Instance members

Name	Description
`this.apply x`

Resize module

Function	Description
`create height width`

create

create height width

Parameters

height : int
width : int

Returns Resize

RandomHorizontalFlip

Randomly flip the image horizontally with probability p. Input: $[C, H, W]$ or $[B, C, H, W]$ .

Record fields

Name	Description
`P`

Instance members

Name	Description
`this.apply x`

RandomHorizontalFlip module

Function	Description
`create p`
`defaultFlip`

create

create p

Parameters

p : float

Returns RandomHorizontalFlip

defaultFlip

defaultFlip

Returns RandomHorizontalFlip

RandomVerticalFlip

Randomly flip the image vertically with probability p. Input: $[C, H, W]$ or $[B, C, H, W]$ .

Record fields

Name	Description
`P`

Instance members

Name	Description
`this.apply x`

RandomVerticalFlip module

Function	Description
`create p`
`defaultFlip`

create

create p

Parameters

p : float

Returns RandomVerticalFlip

defaultFlip

defaultFlip

Returns RandomVerticalFlip

RandomCrop

Randomly crop the image to the given size. Input: $[C, H, W]$ or $[B, C, H, W]$ .

Record fields

Name	Description
`Height`
`Width`

Instance members

Name	Description
`this.apply x`

RandomCrop module

Function	Description
`create height width`

create

create height width

Parameters

height : int
width : int

Returns RandomCrop

CenterCrop

Crop the center region of the image. Input: $[C, H, W]$ or $[B, C, H, W]$ .

Record fields

Name	Description
`Height`
`Width`

Instance members

Name	Description
`this.apply x`

CenterCrop module

Function	Description
`create height width`

create

create height width

Parameters

height : int
width : int

Returns CenterCrop

ToGrayscale

Convert an RGB image to grayscale using ITU-R BT.601 weights. Input: $[3, H, W]$ or $[B, 3, H, W]$ .

Record fields

Name	Description
`NumOutputChannels`

Instance members

Name	Description
`this.apply x`

ToGrayscale module

Function	Description
`create numOutputChannels`
`single`
`triple`

create

create numOutputChannels

Parameters

numOutputChannels : int

Returns ToGrayscale

single

single

Returns ToGrayscale

triple

triple

Returns ToGrayscale

ConvertImageDType

Convert image tensor dtype, scaling between [0, 255] int and [0.0, 1.0] float ranges. Input: any image tensor.

Record fields

Name	Description
`TargetDType`

Instance members

Name	Description
`this.apply x`

ConvertImageDType module

Function	Description
`create dtype`

create

create dtype

Parameters

dtype : ScalarType

Returns ConvertImageDType