HLS#

Tip

Functions#

kornia.color.rgb_to_hls(image, eps=1e-8)[source]#

Convert an RGB image to HLS.

The image data is assumed to be in the range of (0, 1).

Convention:: Channels are H, L, S at axis -3. Hue is measured in radians in [0, 2π), unlike OpenCV, which uses degrees (halved for 8-bit images).

NOTE: this method cannot be compiled with JIT in pytohrch < 1.7.0

Parameters:

image (Tensor) – RGB image to be converted to HLS with shape \((*, 3, H, W)\).
eps (float, optional) – bias added to the chroma and lightness denominators before dividing. The zero denominators themselves are handled by a safe-substitution guard, so eps is not what keeps the result finite and eps=0 is well defined. Default: 1e-8

Return type:

Tensor

Returns:

HLS version of the image with shape \((*, 3, H, W)\).

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> output = rgb_to_hls(input)  # 2x3x4x5

kornia.color.hls_to_rgb(image)[source]#

Convert a HLS image to RGB.

The image data is assumed to be in the range of (0, 1).

Parameters:: image (Tensor) – HLS image to be converted to RGB with shape \((*, 3, H, W)\).
Return type:: Tensor
Returns:: RGB version of the image with shape \((*, 3, H, W)\).

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> output = hls_to_rgb(input)  # 2x3x4x5

class kornia.color.RgbToHls(*args, **kwargs)[source]#

Convert an image from RGB to HLS.

See the Convention block on rgb_to_hls().

The image data is assumed to be in the range of (0, 1).

Shape:

Examples

>>> input = torch.rand(2, 3, 4, 5)
>>> hls = RgbToHls()
>>> output = hls(input)  # 2x3x4x5

class kornia.color.HlsToRgb(*args, **kwargs)[source]#

Convert an image from HLS to RGB.

See the Convention block on hls_to_rgb().

The image data is assumed to be in the range of (0, 1).

Shape:

Reference:

https://en.wikipedia.org/wiki/HSL_and_HSV

Examples

>>> input = torch.rand(2, 3, 4, 5)
>>> rgb = HlsToRgb()
>>> output = rgb(input)  # 2x3x4x5