habana_frameworks.mediapipe.fn.ColorSpaceConversion

Class:
  • habana_frameworks.mediapipe.fn.ColorSpaceConversion(**kwargs)

Define graph call:
  • __call__(input)

Parameter:
  • input - Input tensor to operator. Supported dimensions: minimum = 4, maximum = 4. Supported data types: UINT8, UINT16.

Description:

Transforms the image from one color representation to another color representation.

Supported backend:
  • HPU

Keyword Arguments

kwargs

Description

colorSpaceMode

Color space mode to be selected.

  • Type: int

  • Default: 1

  • Optional: yes

  • Supported modes:

    • RGB_TO_YCBCR: 0

    • RGB_TO_BGR: 1

    • YCBCR_TO_RGB: 2

    • YCBCR_TO_BGR: 3

    • BGR_TO_RGB: 4

    • BGR_TO_YCBCR: 5

    • GRAY_TO_RGB: 6

    • GRAY_TO_BGR: 7

    • GRAY_TO_YCBCR: 8

    • RGB_TO_GRAY: 9

    • YCBCR_TO_GRAY: 10

    • BGR_TO_GRAY: 11

dtype

Output data type.

  • Type: habana_frameworks.mediapipe.media_types.dtype

  • Default: UINT8

  • Optional: yes

  • Supported data types:

    • UINT8

Example: ColorSpaceConversion Operator

The following code snippet shows usage of ColorSpaceConversion operator:

from habana_frameworks.mediapipe import fn
from habana_frameworks.mediapipe.mediapipe import MediaPipe
from habana_frameworks.mediapipe.media_types import imgtype as it
from habana_frameworks.mediapipe.media_types import dtype as dt
import matplotlib.pyplot as plt

# Create media pipeline derived class
class myMediaPipe(MediaPipe):
    def __init__(self, device, dir, queue_depth, batch_size, img_h, img_w):
        super(
            myMediaPipe,
            self).__init__(
            device,
            queue_depth,
            batch_size,
            self.__class__.__name__)

        self.input = fn.ReadImageDatasetFromDir(shuffle=False,
                                                dir=dir,
                                                format="jpg")

        # WHCN
        self.decode = fn.ImageDecoder(device="hpu",
                                      output_format=it.RGB_P,
                                      resize=[img_w, img_h])

        self.color_space_conversion = fn.ColorSpaceConversion(colorSpaceMode=1,
                                                              dtype=dt.UINT8)

        # WHCN -> CWHN
        self.transpose = fn.Transpose(permutation=[2, 0, 1, 3],
                                      tensorDim=4,
                                      dtype=dt.UINT8)

    def definegraph(self):
        images, labels = self.input()
        images = self.decode(images)
        images = self.color_space_conversion(images)
        images = self.transpose(images)
        return images, labels

def display_images(images, batch_size, cols):
    rows = (batch_size + 1) // cols
    plt.figure(figsize=(10, 10))
    for i in range(batch_size):
        ax = plt.subplot(rows, cols, i + 1)
        plt.imshow(images[i])
        plt.axis("off")
    plt.show()

def main():
    batch_size = 6
    img_width = 200
    img_height = 200
    img_dir = "/path/to/images"
    queue_depth = 2
    columns = 3

    # Create media pipeline object
    pipe = myMediaPipe('hpu', img_dir, queue_depth, batch_size,
                        img_height, img_width)

    # Build media pipeline
    pipe.build()

    # Initialize media pipeline iterator
    pipe.iter_init()

    # Run media pipeline
    images, labels = pipe.run()

    # Copy data to host from device as numpy array
    images = images.as_cpu().as_nparray()
    labels = labels.as_cpu().as_nparray()

    # Display images
    display_images(images, batch_size, columns)


if __name__ == "__main__":
    main()

Color Space RGB to BGR Converted Images 1

Image1 of decoded batch and cropped.
Image2 of decoded batch and cropped.
Image3 of decoded batch and cropped.
Image4 of decoded batch and cropped.
Image5 of decoded batch and cropped.
Image6 of decoded batch and cropped.
1

Licensed under a CC BY SA 4.0 license. The images used here are taken from https://data.caltech.edu/records/mzrjq-6wc02.