RandomPhotometricDistort

class torchaug.transforms.RandomPhotometricDistort(brightness=(0.875, 1.125), contrast=(0.5, 1.5), saturation=(0.5, 1.5), hue=(-0.05, 0.05), p_transform=0.5, p=0.5, batch_inplace=False, num_chunks=1, permute_chunks=False, batch_transform=False)[source]

Randomly distorts the image or video as used in SSD: Single Shot MultiBox Detector.

This transform relies on ColorJitter under the hood to adjust the contrast, saturation, hue, brightness, and also randomly permutes channels.

Parameters:

  • brightness (Tuple[float, float], optional) – How much to jitter brightness. brightness_factor is chosen uniformly from [min, max]. Should be non negative numbers. Default: (0.875, 1.125)

  • contrast (Tuple[float, float], optional) – How much to jitter contrast. contrast_factor is chosen uniformly from [min, max]. Should be non-negative numbers. Default: (0.5, 1.5)

  • saturation (Tuple[float, float], optional) – How much to jitter saturation. saturation_factor is chosen uniformly from [min, max]. Should be non negative numbers. Default: (0.5, 1.5)

  • hue (Tuple[float, float], optional) – How much to jitter hue. hue_factor is chosen uniformly from [min, max]. Should have -0.5 <= min <= max <= 0.5. To jitter hue, the pixel values of the input image has to be non-negative for conversion to HSV space; thus it does not work if you normalize your image to an interval with negative values, or use an interpolation that generates negative values before using this function. Default: (-0.05, 0.05)

  • p_transform (float, optional) – probability each distortion operation (contrast, saturation, …) to be applied. Default: 0.5

  • p (float, optional) – probability of the image being photometrically distorted. Default: 0.5

  • batch_inplace (bool, optional) – whether to apply the batch transform in-place. Does not prevent functionals to make copy but can reduce time and memory consumption. Default: False

  • num_chunks (int, optional) – number of chunks to split the batched input into. Default: 1

  • permute_chunks (bool, optional) – whether to permute the chunks. Default: False

  • batch_transform (bool, optional) – whether to apply the transform in batch mode. Default: False