habana_frameworks.mediapipe.fn.Contrast

Class:

• habana_frameworks.mediapipe.fn.Contrast(**kwargs)

Define graph call:

• __call__(input, contrast_tensor)

Parameter:

• input - Input tensor to operator. Supported dimensions: minimum = 1, maximum = 4. Supported data types: UINT8, UINT16.

• (optional) contrast_tensor - Tensor containing contrast value for each image in the batch. Supported dimensions: minimum = 1, maximum = 1. Supported data type: FLOAT32.

Description:

This operator is used to change the contrast of the image. It scales each pixel in the image data with contrast scale. If contrast_tensor is not provided then scalar value is used for all the images. The equation for obtaining output pixel value is: output = input * contrast_scale + (1 - contrast_scale) * 128.

Supported backend:

• HPU

Keyword Arguments

kwargs	Description
contrast_scale	Contrast scale factor required for pixel manipulation. Type: float Default: 0.0 Optional: yes
dtype	Output data type. Type: habana_frameworks.mediapipe.media_types.dtype Default: UINT8 Optional: yes Supported data type: UINT8 UINT16

Note

1. Input/output tensor must be of the same data type.

2. Input1 and output tensor could be in any layout but both have to be same.

3. Input2 is one dimensional tensor of size N.

4. Contrast value can be provided either as scalar or 1D tensor.

Example: Contrast Operator

The following code snippet shows usage of Contrast 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.contrast = fn.Contrast(contrast_scale=2.5,
                                    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.contrast(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 CPU 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()

Images with Changed Contrast 1

1

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