Grayscale#

Tip

Learn more: https://en.wikipedia.org/wiki/Grayscale

Functions#

kornia.color.rgb_to_grayscale(image, rgb_weights=None)[source]#

Convert a RGB image to grayscale version of image.

Try in browser

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

Convention:: RGB is channel-first at axis -3 and the result has one channel. Default weights are ITU-R BT.601 luma weights (0.299, 0.587, 0.114) in RGB order.

Warning

Explicit rgb_weights expect a floating image: they are cast to the image’s dtype, so on an integer image float weights truncate to zero and integer weights wrap. With the default weights a uint8 image is converted exactly, bit for bit as cv2.cvtColor(img, cv2.COLOR_RGB2GRAY) does.

Parameters:

image (Tensor) – RGB image to be converted to grayscale with shape \((*,3,H,W)\).
rgb_weights (Optional[Tensor], optional) – Weights that will be applied on each channel (RGB). The sum of the weights should add up to one. Default: None

Return type:

Tensor

Returns:

grayscale version of the image with shape \((*,1,H,W)\).

Note

See a working example here.

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> gray = rgb_to_grayscale(input) # 2x1x4x5

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

Convert a BGR image to grayscale.

Try in browser

The image data is assumed to be in the range of (0, 1). First flips to RGB, then converts.

Convention:: BGR is channel-first at axis -3. This uses the RGB luma weights after reversing channel order.

Parameters:: image (Tensor) – BGR image to be converted to grayscale with shape \((*,3,H,W)\).
Return type:: Tensor
Returns:: grayscale version of the image with shape \((*,1,H,W)\).

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> gray = bgr_to_grayscale(input) # 2x1x4x5

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

Convert a grayscale image to RGB version of image.

Try in browser

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

Convention:: The singleton channel at axis -3 is repeated into R, G and B. Leading dimensions are preserved.

Parameters:: image (Tensor) – grayscale image torch.Tensor to be converted to RGB with shape \((*,1,H,W)\).
Return type:: Tensor
Returns:: RGB version of the image with shape \((*,3,H,W)\).

Example

>>> input = torch.randn(2, 1, 4, 5)
>>> gray = grayscale_to_rgb(input) # 2x3x4x5

Modules#

class kornia.color.RgbToGrayscale(rgb_weights=None)[source]#

nn.Module to convert a RGB image to grayscale version of image.

Try in browser

See the Convention block on rgb_to_grayscale().

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

Shape:

image: \((*, 3, H, W)\)
output: \((*, 1, H, W)\)

reference:

https://docs.opencv.org/4.0.1/de/d25/imgproc_color_conversions.html

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> gray = RgbToGrayscale()
>>> output = gray(input)  # 2x1x4x5

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

nn.Module to convert a BGR image to grayscale version of image.

See the Convention block on bgr_to_grayscale().

The image data is assumed to be in the range of (0, 1). First flips to RGB, then converts.

Shape:

image: \((*, 3, H, W)\)
output: \((*, 1, H, W)\)

reference:

https://docs.opencv.org/4.0.1/de/d25/imgproc_color_conversions.html

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> gray = BgrToGrayscale()
>>> output = gray(input)  # 2x1x4x5

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

nn.Module to convert a grayscale image to RGB version of image.

Try in browser

See the Convention block on grayscale_to_rgb().

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

Shape:

image: \((*, 1, H, W)\)
output: \((*, 3, H, W)\)

reference:

https://docs.opencv.org/4.0.1/de/d25/imgproc_color_conversions.html

Example

>>> input = torch.rand(2, 1, 4, 5)
>>> rgb = GrayscaleToRgb()
>>> output = rgb(input)  # 2x3x4x5