File size: 4,628 Bytes
b84549f |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 |
# Copyright 2019 Google LLC
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# https://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
"""Base augmentations operators."""
import numpy as np
from PIL import Image, ImageOps, ImageEnhance
# ImageNet code should change this value
IMAGE_SIZE = 28
def int_parameter(level, maxval):
"""Helper function to scale `val` between 0 and maxval .
Args:
level: Level of the operation that will be between [0, `PARAMETER_MAX`].
maxval: Maximum value that the operation can have. This will be scaled to
level/PARAMETER_MAX.
Returns:
An int that results from scaling `maxval` according to `level`.
"""
return int(level * maxval / 10)
def float_parameter(level, maxval):
"""Helper function to scale `val` between 0 and maxval.
Args:
level: Level of the operation that will be between [0, `PARAMETER_MAX`].
maxval: Maximum value that the operation can have. This will be scaled to
level/PARAMETER_MAX.
Returns:
A float that results from scaling `maxval` according to `level`.
"""
return float(level) * maxval / 10.
def sample_level(n):
return np.random.uniform(low=0.1, high=n)
def autocontrast(pil_img, _):
return ImageOps.autocontrast(pil_img)
def equalize(pil_img, _):
return ImageOps.equalize(pil_img)
def posterize(pil_img, level):
level = int_parameter(sample_level(level), 4)
return ImageOps.posterize(pil_img, 4 - level)
def rotate(pil_img, level):
degrees = int_parameter(sample_level(level), 30)
if np.random.uniform() > 0.5:
degrees = -degrees
return pil_img.rotate(degrees, resample=Image.BILINEAR)
def solarize(pil_img, level):
level = int_parameter(sample_level(level), 256)
return ImageOps.solarize(pil_img, 256 - level)
def shear_x(pil_img, level):
level = float_parameter(sample_level(level), 0.3)
if np.random.uniform() > 0.5:
level = -level
return pil_img.transform((IMAGE_SIZE, IMAGE_SIZE),
Image.AFFINE, (1, level, 0, 0, 1, 0),
resample=Image.BILINEAR)
def shear_y(pil_img, level):
level = float_parameter(sample_level(level), 0.3)
if np.random.uniform() > 0.5:
level = -level
return pil_img.transform((IMAGE_SIZE, IMAGE_SIZE),
Image.AFFINE, (1, 0, 0, level, 1, 0),
resample=Image.BILINEAR)
def translate_x(pil_img, level):
level = int_parameter(sample_level(level), IMAGE_SIZE / 3)
if np.random.random() > 0.5:
level = -level
return pil_img.transform((IMAGE_SIZE, IMAGE_SIZE),
Image.AFFINE, (1, 0, level, 0, 1, 0),
resample=Image.BILINEAR)
def translate_y(pil_img, level):
level = int_parameter(sample_level(level), IMAGE_SIZE / 3)
if np.random.random() > 0.5:
level = -level
return pil_img.transform((IMAGE_SIZE, IMAGE_SIZE),
Image.AFFINE, (1, 0, 0, 0, 1, level),
resample=Image.BILINEAR)
# operation that overlaps with ImageNet-C's test set
def color(pil_img, level):
level = float_parameter(sample_level(level), 1.8) + 0.1
return ImageEnhance.Color(pil_img).enhance(level)
# operation that overlaps with ImageNet-C's test set
def contrast(pil_img, level):
level = float_parameter(sample_level(level), 1.8) + 0.1
return ImageEnhance.Contrast(pil_img).enhance(level)
# operation that overlaps with ImageNet-C's test set
def brightness(pil_img, level):
level = float_parameter(sample_level(level), 1.8) + 0.1
return ImageEnhance.Brightness(pil_img).enhance(level)
# operation that overlaps with ImageNet-C's test set
def sharpness(pil_img, level):
level = float_parameter(sample_level(level), 1.8) + 0.1
return ImageEnhance.Sharpness(pil_img).enhance(level)
augmentations = [
autocontrast, equalize, posterize, rotate, solarize, shear_x, shear_y,
translate_x, translate_y
]
augmentations_all = [
autocontrast, equalize, posterize, rotate, solarize, shear_x, shear_y,
translate_x, translate_y, color, contrast, brightness, sharpness
] |