RGB#

Tip

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

Functions#

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

Convert a RGB image to BGR.

Try in browser

Convention:: Reverses the three channels at axis -3; leading dimensions are preserved.

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

Example

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

kornia.color.rgb_to_rgb255(image)[source]#

Convert an image from RGB to RGB [0, 255] for visualization purposes.

Convention:: Multiplies unit-range RGB values by 255 and clamps the result to [0, 255].

Parameters:: image (Tensor) – RGB Image to be converted to RGB [0, 255] of shape \((*,3,H,W)\).
Return type:: Tensor
Returns:: RGB version of the image with shape of shape \((*,3,H,W)\).

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> output = rgb_to_rgb255(input) # 2x3x4x5

kornia.color.rgb255_to_rgb(image)[source]#

Convert an image from RGB [0, 255] to RGB for visualization purposes.

Convention:: Divides RGB255 values by 255 without clipping.

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

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> output = rgb255_to_rgb(input) # 2x3x4x5

kornia.color.rgb255_to_normals(image)[source]#

Convert an image from RGB [0, 255] to surface normals for visualization purposes.

Convention:: Maps RGB255 channels to [-1, 1], then normalizes each three-channel vector at axis -3. Half inputs are computed in float32 and rounded to the input dtype once at return.

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

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> output = rgb255_to_normals(input) # 2x3x4x5

kornia.color.normals_to_rgb255(image)[source]#

Convert surface normals to RGB [0, 255] for visualization purposes.

Convention:: Maps normal components from [-1, 1] to RGB255 channels [0, 255], clamping the result.

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

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> output = normals_to_rgb255(input) # 2x3x4x5

Modules#

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

Convert an image from RGB to BGR.

Try in browser

See the Convention block on rgb_to_bgr().

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

Returns:: BGR version of the image.

Shape:

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

Example

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

class kornia.color.RgbToRgb255(*args, **kwargs)[source]#

Convert an image from RGB to RGB [0, 255] for visualization purposes.

See the Convention block on rgb_to_rgb255().

Returns:: RGB version of the image.

Shape:

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

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> rgb = RgbToRgb255()
>>> output = rgb(input)  # 2x3x4x5

class kornia.color.Rgb255ToRgb(*args, **kwargs)[source]#

Convert an image from RGB [0, 255] to RGB for visualization purposes.

See the Convention block on rgb255_to_rgb().

Returns:: RGB version of the image.

Shape:

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

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> rgb = Rgb255ToRgb()
>>> output = rgb(input)  # 2x3x4x5

class kornia.color.Rgb255ToNormals(*args, **kwargs)[source]#

Convert an image from RGB [0, 255] to surface normals for visualization purposes.

See the Convention block on rgb255_to_normals().

Returns:: surface normals version of the image.

Shape:

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

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> normals = Rgb255ToNormals()
>>> output = normals(input)  # 2x3x4x5

class kornia.color.NormalsToRgb255(*args, **kwargs)[source]#

Convert surface normals to RGB [0, 255] for visualization purposes.

See the Convention block on normals_to_rgb255().

Returns:: RGB version of the image.

Shape:

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

Example

>>> input = torch.rand(2, 3, 4, 5)
>>> rgb = NormalsToRgb255()
>>> output = rgb(input)  # 2x3x4x5