def augmentation(mode, target_size, prob=0.5, aug_m=2):
'''
description: augmentation
mode: 'train' 'test'
target_size: int or list, the shape of image ,
aug_m: Strength of transform
'''
high_p = prob
low_p = high_p / 2.0
M = aug_m
first_size = [int(x / 0.7) for x in target_size]
if mode == 'train':
return composition.Compose([
transforms.Resize(first_size[0], first_size[1], interpolation=3),
transforms.Flip(p=0.5),
composition.OneOf([
RandomCenterCut(scale=0.1 * M),
transforms.ShiftScaleRotate(shift_limit=0.05 * M,
scale_limit=0.1 * M,
rotate_limit=180,
border_mode=cv2.BORDER_CONSTANT,
value=0),
albumentations.imgaug.transforms.IAAAffine(
shear=(-10 * M, 10 * M), mode='constant')
],
p=high_p),
transforms.RandomBrightnessContrast(
brightness_limit=0.1 * M, contrast_limit=0.03 * M, p=high_p),
transforms.HueSaturationValue(hue_shift_limit=5 * M,
sat_shift_limit=15 * M,
val_shift_limit=10 * M,
p=high_p),
transforms.OpticalDistortion(distort_limit=0.03 * M,
shift_limit=0,
border_mode=cv2.BORDER_CONSTANT,
value=0,
p=low_p),
composition.OneOf([
transforms.Blur(blur_limit=7),
albumentations.imgaug.transforms.IAASharpen(),
transforms.GaussNoise(var_limit=(2.0, 10.0), mean=0),
transforms.ISONoise()
],
p=low_p),
transforms.Resize(target_size[0], target_size[1], interpolation=3),
transforms.Normalize(mean=(0.5, 0.5, 0.5),
std=(0.5, 0.5, 0.5),
max_pixel_value=255.0)
],
p=1)
else:
return composition.Compose([
transforms.Resize(target_size[0], target_size[1], interpolation=3),
transforms.Normalize(mean=(0.5, 0.5, 0.5),
std=(0.5, 0.5, 0.5),
max_pixel_value=255.0)
],
p=1)
def get_presize_combine_transforms_V4():
transforms_presize = A.Compose([
transforms.PadIfNeeded(600, 800),
geometric.Perspective(
scale=[0, .1],
pad_mode=cv2.BORDER_REFLECT,
interpolation=cv2.INTER_AREA, p = .3),
transforms.Flip(),
geometric.ShiftScaleRotate(interpolation=cv2.INTER_LANCZOS4, p = 0.95, scale_limit=0.0),
crops.RandomResizedCrop(
TARGET_SIZE, TARGET_SIZE,
scale=(config['rrc_scale_min'], config['rrc_scale_max']),
ratio=(.70, 1.4),
interpolation=cv2.INTER_CUBIC,
p=1.0),
transforms.Transpose()
#rotate.Rotate(interpolation=cv2.INTER_LANCZOS4, p = 0.99),
])
transforms_postsize = A.Compose([
#imgaug.IAAPiecewiseAffine(),
transforms.CoarseDropout(),
transforms.CLAHE(p=.1),
transforms.RandomToneCurve(scale=.1, p=0.2),
transforms.RandomBrightnessContrast(
brightness_limit=.1,
contrast_limit=0.4,
p=.8),
transforms.HueSaturationValue(
hue_shift_limit=20,
sat_shift_limit=50,
val_shift_limit=0,
p=0.5),
transforms.Equalize(p=0.05),
transforms.FancyPCA(p=0.05),
transforms.RandomGridShuffle(p=0.1),
A.OneOf([
transforms.MotionBlur(blur_limit=(3, 9)),
transforms.GaussianBlur(),
transforms.MedianBlur()
], p=0.1),
transforms.ISONoise(p=.2),
transforms.GaussNoise(var_limit=127., p=.3),
A.OneOf([
transforms.GridDistortion(interpolation=cv2.INTER_AREA, distort_limit=[0.7, 0.7], p=0.5),
transforms.OpticalDistortion(interpolation=cv2.INTER_AREA, p=.3),
], p=.3),
geometric.ElasticTransform(alpha=4, sigma=4, alpha_affine=4, interpolation=cv2.INTER_AREA, p=0.3),
transforms.CoarseDropout(),
transforms.Normalize(),
ToTensorV2()
])
return transforms_presize, transforms_postsize
def get_presize_combine_tune_transforms():
transforms_presize = A.Compose([
transforms.Transpose(),
transforms.Flip(),
#transforms.PadIfNeeded(600, 800),
crops.RandomResizedCrop(
TARGET_SIZE, TARGET_SIZE,
scale=(.75, 1),
interpolation=cv2.INTER_CUBIC,
p=1.0),
rotate.Rotate(interpolation=cv2.INTER_LANCZOS4, p = 0.99),
])
transforms_postsize = A.Compose([
transforms.CoarseDropout(),
# transforms.CLAHE(p=.1),
transforms.RandomToneCurve(scale=.1),
transforms.RandomBrightnessContrast(
brightness_limit=.1,
contrast_limit=0.2,
p=.7),
transforms.HueSaturationValue(
hue_shift_limit=20,
sat_shift_limit=60,
val_shift_limit=0,
p=0.6),
#transforms.Equalize(p=0.1),
#transforms.FancyPCA(p=0.05),
#transforms.RandomGridShuffle(p=0.1),
#A.OneOf([
# transforms.MotionBlur(blur_limit=(3, 9)),
# transforms.GaussianBlur(),
# transforms.MedianBlur()
# ], p=0.2),
transforms.ISONoise(p=.3),
transforms.GaussNoise(var_limit=255., p=.3),
#A.OneOf([
# transforms.GridDistortion(interpolation=cv2.INTER_AREA, distort_limit=[0.7, 0.7], p=0.5),
# transforms.OpticalDistortion(interpolation=cv2.INTER_AREA, p=.3),
# ], p=.3),
geometric.ElasticTransform(alpha=4, sigma=100, alpha_affine=100, interpolation=cv2.INTER_AREA, p=0.3),
transforms.CoarseDropout(),
transforms.Normalize(),
ToTensorV2()
])
return transforms_presize, transforms_postsize
def get_augmentations():
"""Get a list of 'major' and 'minor' augmentation functions for the pipeline in a dictionary."""
return {
"major": {
"shift-scale-rot":
trans.ShiftScaleRotate(
shift_limit=0.05,
rotate_limit=35,
border_mode=cv2.BORDER_REPLICATE,
always_apply=True,
),
"crop":
trans.RandomResizedCrop(100,
100,
scale=(0.8, 0.95),
ratio=(0.8, 1.2),
always_apply=True),
# "elastic": trans.ElasticTransform(
# alpha=0.8,
# alpha_affine=10,
# sigma=40,
# border_mode=cv2.BORDER_REPLICATE,
# always_apply=True,
# ),
"distort":
trans.OpticalDistortion(0.2, always_apply=True),
},
"minor": {
"blur":
trans.GaussianBlur(7, always_apply=True),
"noise":
trans.GaussNoise((20.0, 40.0), always_apply=True),
"bright-contrast":
trans.RandomBrightnessContrast(0.4, 0.4, always_apply=True),
"hsv":
trans.HueSaturationValue(30, 40, 50, always_apply=True),
"rgb":
trans.RGBShift(always_apply=True),
"flip":
trans.HorizontalFlip(always_apply=True),
},
}
def get_train_transforms():
return A.Compose([
transforms.PadIfNeeded(600, 800),
geometric.ShiftScaleRotate(interpolation=cv2.INTER_LANCZOS4, p = 0.99, scale_limit=0.8),
geometric.Perspective(pad_mode=cv2.BORDER_REFLECT,interpolation=cv2.INTER_AREA),
crops.RandomResizedCrop(
TARGET_SIZE, TARGET_SIZE,
scale=(config['rrc_scale_min'], config['rrc_scale_max']),
interpolation=cv2.INTER_CUBIC,
p=1.0),
transforms.Transpose(),
transforms.Flip(),
transforms.CoarseDropout(),
transforms.CLAHE(p=.1),
transforms.RandomToneCurve(scale=.1),
transforms.RandomBrightnessContrast(
brightness_limit=.1,
contrast_limit=0.3,
p=.7),
transforms.HueSaturationValue(
hue_shift_limit=20,
sat_shift_limit=60,
val_shift_limit=0,
p=0.6),
transforms.RandomGridShuffle(p=0.1),
A.OneOf([
transforms.MotionBlur(blur_limit=(3, 9)),
transforms.GaussianBlur(),
transforms.MedianBlur()
], p=0.2),
transforms.ISONoise(p=.3),
transforms.GaussNoise(var_limit=255., p=.3),
A.OneOf([
transforms.GridDistortion(interpolation=cv2.INTER_AREA, distort_limit=[0.7, 0.7], p=0.5),
transforms.OpticalDistortion(interpolation=cv2.INTER_AREA, p=.3),
], p=.3),
geometric.ElasticTransform(alpha=4, sigma=100, alpha_affine=100, interpolation=cv2.INTER_AREA, p=0.3),
transforms.CoarseDropout(),
transforms.Normalize(),
ToTensorV2()
])
def __init__(self, im_paths=None, labels=None, phase=None, resize=False):
"""
Args:
im_paths (numpy): image_data
y (numpy): label data
transform: pytorch transforms for transforms and tensor conversion
"""
self.im_paths = im_paths
self.labels = labels
self.resize = resize
self.albumentations_transform = {
'train':
Compose([
ab_transforms.HorizontalFlip(p=0.2),
ab_transforms.VerticalFlip(p=0.2),
ab_transforms.Rotate(limit=180, p=0.2),
ab_transforms.HueSaturationValue(p=0.1),
ab_transforms.RandomContrast(p=0.1),
ab_transforms.GaussianBlur(blur_limit=3, p=0.2),
ab_transforms.GaussNoise(p=0.05),
ab_transforms.CLAHE(p=0.2),
ab_transforms.Normalize(mean=[0.5944, 0.4343, 0.5652],
std=[0.2593, 0.2293, 0.2377]),
ToTensor()
]),
'val':
Compose([
ab_transforms.Normalize(mean=[0.5944, 0.4343, 0.5652],
std=[0.2593, 0.2293, 0.2377]),
ToTensor()
]),
}
if phase == 'train':
self.transform = self.albumentations_transform['train']
else:
self.transform = self.albumentations_transform['val']
def GaussNoise(var_limit=(10.0, 50.0), mean=0, p=0.5):
return transforms.GaussNoise(var_limit=var_limit, mean=mean, p=p)