habana_frameworks.mediapipe.fn.RandomUniform

Class:

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

Define graph call:

• __call__(seed)

Parameter:

• (optional) seed - 1D tensor of size 1. Supported dimensions: minimum = 1, maximum = 1. Supported data types: INT32.

Description:

Generate random numbers from a uniform distribution.

Supported backend:

• HPU, CPU

Keyword Arguments

kwargs	Description
low	Lower bound. Type: float Default: 0.0 Optional: yes
high	Upper bound. Type: float Default: 1.0 Optional: yes
seed	Seed to the random number generator. Type: int Default: 0.0 Optional: yes
dtype	Output data type. Type: habana_frameworks.mediapipe.media_types.dtype Default: FLOAT32 Optional: yes Supported data types: BFLOAT16 FLOAT32

Note

1. If seed tensor is provided, then no need to initialize seed value in operator arguments.

2. Output tensor supported with minimum rank = 1 and maximum rank = 1.

Example: RandomUniform Operator

The following code snippet shows usage of RandomUniform operator. Random data is generated as noise by RandomUniform operator and added to the image:

from habana_frameworks.mediapipe import fn
from habana_frameworks.mediapipe.mediapipe import MediaPipe
from habana_frameworks.mediapipe.media_types import dtype as dt
import numpy as np
import glob

# Create media pipeline derived class
class myMediaPipe(MediaPipe):
    def __init__(self, device, queue_depth, patch_size, num_channels, batch_size, num_threads, img_list, lbl_list, seed):
        super(myMediaPipe, self).__init__(
            device,
            queue_depth,
            batch_size,
            num_threads,
            self.__class__.__name__)

        self.images = fn.ReadNumpyDatasetFromDir(device=device,
                                                num_outputs=1,
                                                shuffle=False,
                                                shuffle_across_dataset=False,
                                                file_list=img_list,
                                                dtype=[dt.FLOAT32],
                                                dense=False,
                                                seed=seed,
                                                num_slices=1,
                                                slice_index=0,
                                                drop_remainder=True,
                                                pad_remainder=False
                                                )

        self.labels = fn.ReadNumpyDatasetFromDir(device=device,
                                                num_outputs=1,
                                                shuffle=False,
                                                shuffle_across_dataset=False,
                                                file_list=lbl_list,
                                                dtype=[dt.UINT8],
                                                dense=False,
                                                seed=seed,
                                                num_slices=1,
                                                slice_index=0,
                                                drop_remainder=True,
                                                pad_remainder=False
                                                )

        self.crop = fn.RandomBiasedCrop(patch_size=patch_size,
                                        num_channels=num_channels,
                                        seed=seed,
                                        num_workers=4,
                                        cache_bboxes=True,
                                        device=device,
                                        )

        self.random_u = fn.RandomUniform(seed=seed,
                                        low=0.1,
                                        high=0.3,
                                        dtype=dt.FLOAT32,
                                        device=device,
                                        )

        self.mul = fn.Mult(device=device)

    def definegraph(self):
        img = self.images()
        lbl = self.labels()
        img, lbl, coord = self.crop(img, lbl)
        random_scale = self.random_u()
        img_out = self.mul(img, random_scale)
        return img, random_scale, img_out


def main():
    batch_size = 1
    patch_size = [5, 5, 5]
    queue_depth = 2
    num_channels = 1
    num_threads = 1
    dir = "/path/to/numpy/files/"
    pattern0 = "case_*_x.npy"
    pattern1 = "case_*_y.npy"
    image_list = np.array(sorted(glob.glob(dir + "/{}".format(pattern0))))
    label_list = np.array(sorted(glob.glob(dir + "/{}".format(pattern1))))
    device = 'hpu'
    seed = 1234

    # Create media pipeline object
    pipe = myMediaPipe(device, queue_depth, patch_size,
                    num_channels, batch_size, num_threads, image_list, label_list, seed)

    # Build media pipeline
    pipe.build()

    # Initialize media pipeline iterator
    pipe.iter_init()

    # Run media pipeline
    input, random_scale, multiplication = pipe.run()

    if (device == 'cpu'):
        # Copy data as numpy array
        input = input.as_nparray()
        random_scale = random_scale.as_nparray()
        multiplication = multiplication.as_nparray()
    else:
        # Copy data to host from device as numpy array
        input = input.as_cpu().as_nparray()
        random_scale = random_scale.as_cpu().as_nparray()
        multiplication = multiplication.as_cpu().as_nparray()

    print("\nrandom uniform op tensor shape:", random_scale.shape)
    print("\nrandom uniform op tensor dtype:", random_scale.dtype)
    print("\nrandom uniform op tensor data:", random_scale)


if __name__ == "__main__":
    main()

The following is the output of RandomNormal operator:

random uniform op tensor shape: (1,)

random uniform op tensor dtype: float32

random uniform op tensor data: [0.11438505]