File size: 6,996 Bytes
3440f83 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 |
# code in this file is adpated from rpmcruz/autoaugment
# https://github.com/rpmcruz/autoaugment/blob/master/transformations.py
import random
import PIL
# from PIL import ImageOps, ImageEnhance, ImageDraw
import numpy as np
import torch
from PIL import Image
def ShearX(img, v): # [-0.3, 0.3]
assert -0.3 <= v <= 0.3
if random.random() > 0.5:
v = -v
return img.transform(img.size, PIL.Image.AFFINE, (1, v, 0, 0, 1, 0))
def ShearY(img, v): # [-0.3, 0.3]
assert -0.3 <= v <= 0.3
if random.random() > 0.5:
v = -v
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, 0, v, 1, 0))
def TranslateX(img, v): # [-150, 150] => percentage: [-0.45, 0.45]
assert -0.45 <= v <= 0.45
if random.random() > 0.5:
v = -v
v = v * img.size[0]
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, v, 0, 1, 0))
def TranslateXabs(img, v): # [-150, 150] => percentage: [-0.45, 0.45]
assert 0 <= v
if random.random() > 0.5:
v = -v
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, v, 0, 1, 0))
def TranslateY(img, v): # [-150, 150] => percentage: [-0.45, 0.45]
assert -0.45 <= v <= 0.45
if random.random() > 0.5:
v = -v
v = v * img.size[1]
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, 0, 0, 1, v))
def TranslateYabs(img, v): # [-150, 150] => percentage: [-0.45, 0.45]
assert 0 <= v
if random.random() > 0.5:
v = -v
return img.transform(img.size, PIL.Image.AFFINE, (1, 0, 0, 0, 1, v))
def Rotate(img, v): # [-30, 30]
assert -30 <= v <= 30
if random.random() > 0.5:
v = -v
return img.rotate(v)
def AutoContrast(img, _):
return PIL.ImageOps.autocontrast(img)
def Invert(img, _):
return PIL.ImageOps.invert(img)
def Equalize(img, _):
return PIL.ImageOps.equalize(img)
def Flip(img, _): # not from the paper
return PIL.ImageOps.mirror(img)
def Solarize(img, v): # [0, 256]
assert 0 <= v <= 256
return PIL.ImageOps.solarize(img, v)
def SolarizeAdd(img, addition=0, threshold=128):
img_np = np.array(img).astype(np.int)
img_np = img_np + addition
img_np = np.clip(img_np, 0, 255)
img_np = img_np.astype(np.uint8)
img = Image.fromarray(img_np)
return PIL.ImageOps.solarize(img, threshold)
def Posterize(img, v): # [4, 8]
v = int(v)
v = max(1, v)
return PIL.ImageOps.posterize(img, v)
def Contrast(img, v): # [0.1,1.9]
assert 0.1 <= v <= 1.9
return PIL.ImageEnhance.Contrast(img).enhance(v)
def Color(img, v): # [0.1,1.9]
assert 0.1 <= v <= 1.9
return PIL.ImageEnhance.Color(img).enhance(v)
def Brightness(img, v): # [0.1,1.9]
assert 0.1 <= v <= 1.9
return PIL.ImageEnhance.Brightness(img).enhance(v)
def Sharpness(img, v): # [0.1,1.9]
assert 0.1 <= v <= 1.9
return PIL.ImageEnhance.Sharpness(img).enhance(v)
def Cutout(img, v): # [0, 60] => percentage: [0, 0.2]
assert 0.0 <= v <= 0.2
if v <= 0.0:
return img
v = v * img.size[0]
return CutoutAbs(img, v)
def CutoutAbs(img, v): # [0, 60] => percentage: [0, 0.2]
# assert 0 <= v <= 20
if v < 0:
return img
w, h = img.size
x0 = np.random.uniform(w)
y0 = np.random.uniform(h)
x0 = int(max(0, x0 - v / 2.0))
y0 = int(max(0, y0 - v / 2.0))
x1 = min(w, x0 + v)
y1 = min(h, y0 + v)
xy = (x0, y0, x1, y1)
color = (125, 123, 114)
# color = (0, 0, 0)
img = img.copy()
PIL.ImageDraw.Draw(img).rectangle(xy, color)
return img
def SamplePairing(imgs): # [0, 0.4]
def f(img1, v):
i = np.random.choice(len(imgs))
img2 = PIL.Image.fromarray(imgs[i])
return PIL.Image.blend(img1, img2, v)
return f
def Identity(img, v):
return img
def augment_list(): # 16 oeprations and their ranges
# https://github.com/google-research/uda/blob/master/image/randaugment/policies.py#L57
# l = [
# (Identity, 0., 1.0),
# (ShearX, 0., 0.3), # 0
# (ShearY, 0., 0.3), # 1
# (TranslateX, 0., 0.33), # 2
# (TranslateY, 0., 0.33), # 3
# (Rotate, 0, 30), # 4
# (AutoContrast, 0, 1), # 5
# (Invert, 0, 1), # 6
# (Equalize, 0, 1), # 7
# (Solarize, 0, 110), # 8
# (Posterize, 4, 8), # 9
# # (Contrast, 0.1, 1.9), # 10
# (Color, 0.1, 1.9), # 11
# (Brightness, 0.1, 1.9), # 12
# (Sharpness, 0.1, 1.9), # 13
# # (Cutout, 0, 0.2), # 14
# # (SamplePairing(imgs), 0, 0.4), # 15
# ]
# https://github.com/tensorflow/tpu/blob/8462d083dd89489a79e3200bcc8d4063bf362186/models/official/efficientnet/autoaugment.py#L505
l = [
(AutoContrast, 0, 1),
(Equalize, 0, 1),
# (Invert, 0, 1),
(Rotate, 0, 30),
(Posterize, 0, 4),
(Solarize, 0, 256),
(SolarizeAdd, 0, 110),
(Color, 0.1, 1.9),
(Contrast, 0.1, 1.9),
(Brightness, 0.1, 1.9),
(Sharpness, 0.1, 1.9),
(ShearX, 0.0, 0.3),
(ShearY, 0.0, 0.3),
# (CutoutAbs, 0, 40),
(TranslateXabs, 0.0, 100),
(TranslateYabs, 0.0, 100),
]
return l
class Lighting(object):
"""Lighting noise(AlexNet - style PCA - based noise)"""
def __init__(self, alphastd, eigval, eigvec):
self.alphastd = alphastd
self.eigval = torch.Tensor(eigval)
self.eigvec = torch.Tensor(eigvec)
def __call__(self, img):
if self.alphastd == 0:
return img
alpha = img.new().resize_(3).normal_(0, self.alphastd)
rgb = (
self.eigvec.type_as(img)
.clone()
.mul(alpha.view(1, 3).expand(3, 3))
.mul(self.eigval.view(1, 3).expand(3, 3))
.sum(1)
.squeeze()
)
return img.add(rgb.view(3, 1, 1).expand_as(img))
class CutoutDefault(object):
"""
Reference : https://github.com/quark0/darts/blob/master/cnn/utils.py
"""
def __init__(self, length):
self.length = length
def __call__(self, img):
h, w = img.size(1), img.size(2)
mask = np.ones((h, w), np.float32)
y = np.random.randint(h)
x = np.random.randint(w)
y1 = np.clip(y - self.length // 2, 0, h)
y2 = np.clip(y + self.length // 2, 0, h)
x1 = np.clip(x - self.length // 2, 0, w)
x2 = np.clip(x + self.length // 2, 0, w)
mask[y1:y2, x1:x2] = 0.0
mask = torch.from_numpy(mask)
mask = mask.expand_as(img)
img *= mask
return img
class RandAugment:
def __init__(self, n, m):
self.n = n
self.m = m # [0, 30]
self.augment_list = augment_list()
def __call__(self, img):
ops = random.choices(self.augment_list, k=self.n)
for op, minval, maxval in ops:
val = (float(self.m) / 30) * float(maxval - minval) + minval
img = op(img, val)
return img
|