RobustART.noise.utils.imagenet_c package¶
Submodules¶
RobustART.noise.utils.imagenet_c.corruptions module¶
- class RobustART.noise.utils.imagenet_c.corruptions.MotionImage(image=None, blob=None, file=None, filename=None, pseudo=None, background=None, colorspace=None, depth=None, extract=None, format=None, height=None, interlace=None, resolution=None, sampling_factors=None, units=None, width=None)¶
Bases:
wand.image.Image- motion_blur(radius=0.0, sigma=0.0, angle=0.0)¶
Apply a Gaussian blur along an
angledirection. This simulates motion movement.- See
Example of motion_blur.
- Parameters
radius (
numbers.Real) – Aperture size of the Gaussian operator.sigma (
numbers.Real) – Standard deviation of the Gaussian operator.angle (
numbers.Real) – Apply the effect along this angle.
New in version 0.5.4.
- RobustART.noise.utils.imagenet_c.corruptions.brightness(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.clipped_zoom(img, zoom_factor)¶
- RobustART.noise.utils.imagenet_c.corruptions.contrast(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.defocus_blur(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.disk(radius, alias_blur=0.1, dtype=<class 'numpy.float32'>)¶
- RobustART.noise.utils.imagenet_c.corruptions.elastic_transform(image, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.fgsm(x, source_net, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.fog(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.frost(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.gaussian_blur(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.gaussian_noise(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.glass_blur(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.impulse_noise(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.jpeg_compression(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.motion_blur(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.pixelate(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.plasma_fractal(mapsize=256, wibbledecay=3)¶
Generate a heightmap using diamond-square algorithm. Return square 2d array, side length ‘mapsize’, of floats in range 0-255. ‘mapsize’ must be a power of two.
- RobustART.noise.utils.imagenet_c.corruptions.saturate(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.shot_noise(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.snow(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.spatter(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.speckle_noise(x, severity=1)¶
- RobustART.noise.utils.imagenet_c.corruptions.zoom_blur(x, severity=1)¶
Module contents¶
- RobustART.noise.utils.imagenet_c.corrupt(x, severity=1, corruption_name=None, corruption_number=- 1)¶
- Parameters
x – image to corrupt; a PIL image
severity – strength with which to corrupt x; an integer in [0, 5]
corruption_name – specifies which corruption function to call;
- must be one of ‘gaussian_noise’, ‘shot_noise’, ‘impulse_noise’, ‘defocus_blur’,
‘glass_blur’, ‘motion_blur’, ‘zoom_blur’, ‘snow’, ‘frost’, ‘fog’, ‘brightness’, ‘contrast’, ‘elastic_transform’, ‘pixelate’, ‘jpeg_compression’, ‘speckle_noise’, ‘gaussian_blur’, ‘spatter’, ‘saturate’; the last four are validation functions
- Parameters
corruption_number – the position of the corruption_name in the above list;
an integer in [0, 18]; useful for easy looping; 15, 16, 17, 18 are validation corruption numbers :return: the image in numpy corrupted by a corruption function at the given severity; same shape as input