def get_corrupter(self):
distortion_augs = OneOf([OpticalDistortion(p=1),
GridDistortion(p=1)],
p=1)
effects_augs = OneOf([
IAASharpen(p=1),
IAAEmboss(p=1),
IAAPiecewiseAffine(p=1),
IAAPerspective(p=1),
CLAHE(p=1)
],
p=1)
misc_augs = OneOf([
ShiftScaleRotate(p=1),
HueSaturationValue(p=1),
RandomBrightnessContrast(p=1)
],
p=1)
blur_augs = OneOf(
[Blur(p=1),
MotionBlur(p=1),
MedianBlur(p=1),
GaussNoise(p=1)],
p=1)
aug = Compose([distortion_augs, effects_augs, misc_augs, blur_augs])
return aug
def hard_transform(image_size: int = 256, p: float = 0.5, **kwargs):
"""Hard augmentations (on training)"""
_add_transform_default_params(kwargs)
transforms = Compose([
ShiftScaleRotate(
shift_limit=0.1,
scale_limit=0.1,
rotate_limit=15,
border_mode=cv2.BORDER_REFLECT,
p=p,
),
IAAPerspective(scale=(0.02, 0.05), p=p),
OneOf([
HueSaturationValue(p=p),
ToGray(p=p),
RGBShift(p=p),
ChannelShuffle(p=p),
]),
RandomBrightnessContrast(brightness_limit=0.5, contrast_limit=0.5,
p=p),
RandomGamma(p=p),
CLAHE(p=p),
JpegCompression(quality_lower=50, p=p),
PadIfNeeded(image_size, image_size, border_mode=cv2.BORDER_CONSTANT),
], **kwargs)
return transforms
def hard_transform(image_size=224, p=0.5):
transforms = [
Cutout(
num_holes=4,
max_w_size=image_size // 4,
max_h_size=image_size // 4,
p=p
),
ShiftScaleRotate(
shift_limit=0.1,
scale_limit=0.1,
rotate_limit=15,
border_mode=cv2.BORDER_REFLECT,
p=p
),
IAAPerspective(scale=(0.02, 0.05), p=p),
OneOf(
[
HueSaturationValue(p=p),
ToGray(p=p),
RGBShift(p=p),
ChannelShuffle(p=p),
]
),
RandomBrightnessContrast(
brightness_limit=0.5, contrast_limit=0.5, p=p
),
RandomGamma(p=p),
CLAHE(p=p),
JpegCompression(quality_lower=50, p=p),
]
transforms = Compose(transforms)
return transforms
def __init__(self, root_dir= r"C:\Users\Indy-Windows\Desktop\carvana\carvana\data\train", transform=None, image_size=(512, 512)):
#Initialize Directory Tree from current working directory if no directory is provided
self.root_dir = root_dir
self.img_dir = os.path.join(self.root_dir, 'images')
self.mask_dir = os.path.join(self.root_dir, 'masks')
self.img_transform = transform
self.num_img = len(os.listdir(self.img_dir))
self.num_mask = len(os.listdir(self.mask_dir))
self.img_list = os.listdir(self.img_dir)
self.mask_list = os.listdir(self.mask_dir)
self.image_height = image_size[1]
self.image_width = image_size[0]
self.transform = transform
self.album_transform = Compose([
HorizontalFlip(),
ShiftScaleRotate(shift_limit=0.0625, scale_limit=0.2, rotate_limit=45, p=0.2),
OneOf([
ElasticTransform(p=.2),
IAAPerspective(p=.35),
], p=.35)
])
if self.transform == None:
self.transform = self.album_transform
def augmentation_pipeline(self, p=0.5):
return Compose(
[
HorizontalFlip(p=0.5),
OneOf([
IAAAdditiveGaussianNoise(),
GaussNoise(),
], p=0.2),
OneOf(
[
MotionBlur(p=0.2),
#MedianBlur(blur_limit=3, p=0.1),
Blur(blur_limit=3, p=0.1),
],
p=0.1),
OneOf([
ShiftScaleRotate(shift_limit=0.0625,
scale_limit=0.2,
rotate_limit=5,
p=0.9),
IAAPerspective(scale=(.02, .05))
],
p=0.3)
],
p=p)
def hard_transform(image_size: int = 256, p: float = 0.5):
"""Hard augmentations"""
transforms = Compose([
ShiftScaleRotate(
shift_limit=0.1,
scale_limit=0.1,
rotate_limit=15,
border_mode=cv2.BORDER_REFLECT,
p=p,
),
IAAPerspective(scale=(0.02, 0.05), p=p),
OneOf([
HueSaturationValue(p=p),
ToGray(p=p),
RGBShift(p=p),
ChannelShuffle(p=p),
]),
RandomBrightnessContrast(
brightness_limit=0.5, contrast_limit=0.5, p=p
),
RandomGamma(p=p),
CLAHE(p=p),
JpegCompression(quality_lower=50, p=p),
])
return transforms
def main():
a = IAAPerspective(keep_size=False, always_apply=True)
img = np.zeros([100, 100])
img[25:75, 25:75] = 255
key = 0
while key != 27:
transformedImg = a(image=img)['image']
key = imshowWait(img=img,
transformedImg=(transformedImg, transformedImg.shape))
def get_transforms(*, data):
if data == 'train':
return Compose([
HorizontalFlip(p=0.5),
VerticalFlip(p=0.5),
RandomRotate90(p=0.5),
Transpose(p=0.5),
ShiftScaleRotate(scale_limit=0.2,
rotate_limit=0,
shift_limit=0.2,
p=0.2,
border_mode=0),
IAAAdditiveGaussianNoise(p=0.2),
IAAPerspective(p=0.5),
OneOf(
[
CLAHE(p=1),
RandomBrightness(p=1),
RandomGamma(p=1),
],
p=0.9,
),
OneOf(
[
IAASharpen(p=1),
Blur(blur_limit=3, p=1),
MotionBlur(blur_limit=3, p=1),
],
p=0.9,
),
OneOf(
[
RandomContrast(p=1),
HueSaturationValue(p=1),
],
p=0.9,
),
Compose([VerticalFlip(p=0.5),
RandomRotate90(p=0.5)]),
Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
),
ToTensorV2(), #ToTensor(num_classes=2),
])
elif data == 'valid':
return Compose([
Resize(256, 256),
Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
),
ToTensorV2(),
])
def strong_aug(p=0.5):
return Compose([
Resize(IMG_SIZE, IMG_SIZE),
HorizontalFlip(),
OneOf([
IAAPerspective(),
ShiftScaleRotate(shift_limit=0.0625, scale_limit=0.05, rotate_limit=0, p=0.2),
]),
#RandomBrightnessContrast(),
Normalize(),
])
def hard_transforms(image_size):
min_holes, max_holes = 1, 2
size = 30
return [
# Random shifts, stretches and turns with a 50% probability
ShiftScaleRotate(
shift_limit=0.2,
scale_limit=0.2,
rotate_limit=180,
border_mode=BORDER_CONSTANT,
p=0.1
),
IAAPerspective(scale=(0.02, 0.05), p=0.1),
# Random brightness / contrast with a 30% probability
RandomBrightnessContrast(
brightness_limit=0.2, contrast_limit=0.2, p=0.1
),
OneOf([
GaussNoise(var_limit=1.0, p=1.0),
MultiplicativeNoise(multiplier=(0.9, 1), p=1.0)
], p=0.1),
OneOf([
GaussianBlur(blur_limit=3, p=1.0),
Blur(p=1.0),
], p=0.1),
# CoarseDropout(
# min_holes=min_holes,
# max_holes=max_holes,
# # min_height=image_height // 4,
# # max_height=image_height // 4,
# # min_width=image_width // 4,
# # max_width=image_width // 4,
# min_height=size,
# max_height=size,
# min_width=size,
# max_width=size,
# fill_value=0,
# p=1.0
# ),
# Random gamma changes with a 30% probability
RandomGamma(gamma_limit=(85, 115), p=0.1),
ImageCompression(
quality_lower=70,
quality_upper=100,
p=0.1
),
]
def get_geoometric(self):
geometric = [
ShiftScaleRotate(shift_limit=0.0625,
scale_limit=(-.1, .1),
rotate_limit=45,
p=.5),
IAAPerspective(scale=(.05, .2), keep_size=True, p=.1),
# OneOf([
# OpticalDistortion(p=0.3),
# GridDistortion(p=0.3),
# IAAPiecewiseAffine(p=0.3),
# ], p=0.65)
]
return Compose(geometric)
def shiftscalerotate_aug():
augs_list = [
OneOf([
ShiftScaleRotate(scale_limit=.15,
rotate_limit=15,
border_mode=cv2.BORDER_REPLICATE,
p=0.5),
IAAAffine(shear=20, p=0.5),
IAAPerspective(p=0.5),
],
p=0.5),
Normalize(),
ToTensorV2()
]
return Compose(augs_list, p=1)
def strong_aug(p=1.0):
return Compose(
[
RandomSizedCrop((100, HEIGHT), HEIGHT, WIDTH, w2h_ratio=1.0, p=1.0),
Compose(
[
Flip(),
RandomRotate90(),
Transpose(),
OneOf([IAAAdditiveGaussianNoise(), GaussNoise()], p=0.2),
OneOf(
[MedianBlur(blur_limit=3), Blur(blur_limit=3), MotionBlur()]
),
ShiftScaleRotate(args.shift, args.scale, args.rotate),
# min_max_height: (height of crop before resizing)
# crop_height = randint(min_height, max_height), endpoints included
# crop_width = crop_height * w2h_ratio
# height, width: height/width after crop and resize, for convenience, just use args for resize
OneOf(
[
GridDistortion(p=0.5),
ElasticTransform(p=0.5),
IAAPerspective(),
IAAPiecewiseAffine(),
]
),
OneOf(
[
RGBShift(args.r_shift, args.g_shift, args.b_shift),
HueSaturationValue(
args.hue_shift, args.sat_shift, args.val_shift
),
# ChannelShuffle(),
CLAHE(args.clip),
RandomBrightnessContrast(
args.brightness, args.contrast
),
RandomGamma(gamma_limit=(80, 120)),
# ToGray(),
ImageCompression(quality_lower=75, quality_upper=100),
]
),
],
p=p,
),
ToFloat(max_value=255),
]
)
def strong_aug(p=0.5):
return Compose(
[
RandomRotate90(),
Flip(),
Transpose(),
IAAPerspective(),
OneOf([IAAAdditiveGaussianNoise(), GaussNoise()], p=0.2),
OneOf([MotionBlur(p=0.2), MedianBlur(blur_limit=3, p=0.1), Blur(blur_limit=3, p=0.1)], p=0.2),
ShiftScaleRotate(shift_limit=0.0625, scale_limit=0.2, rotate_limit=45, p=0.2),
OneOf([OpticalDistortion(p=0.3), GridDistortion(p=0.1), IAAPiecewiseAffine(p=0.3)], p=0.2),
OneOf([CLAHE(clip_limit=2), IAASharpen(), IAAEmboss(), RandomBrightnessContrast()], p=0.3),
HueSaturationValue(p=0.3),
Resize(256, 256, p=1, always_apply=True),
],
p=p,
)
def train_trasforms_standard(conf):
height = conf['crop_height']
width = conf['crop_width']
return Compose([
RandomSizedCrop2x(height, width, scale_shift=0.5, p=1),
OneOf([IAAPiecewiseAffine(),
IAAPerspective(),
OpticalDistortion(border_mode=cv2.BORDER_CONSTANT),
GridDistortion(border_mode=cv2.BORDER_CONSTANT),
ElasticTransform(border_mode=cv2.BORDER_CONSTANT)],
p=0.3),
RandomBrightnessContrast(),
RandomGamma(),
OneOf([MedianBlur(), GaussianBlur()], p=0.2),
OneOf([IAAAdditiveGaussianNoise(per_channel=True),GaussNoise()])
]
)
def watermark_with_transparency(image, new_object, input_size):
random_angle = random.randint(-30, 30)
new_object = imutils.rotate_bound(new_object, random_angle)
image = Image.fromarray(image)
new_object = Image.fromarray(new_object)
width, height = image.size
mask_width, mask_height = new_object.size
position = random.randint(0,width - mask_width), random.randint(0,height - mask_height)
mask = np.array(new_object)
mask_1 = mask < 240
mask_2 = mask > 5
mask = np.array(mask_1 & mask_2, dtype='uint8')*255
#return mask
mask = Image.fromarray(mask[:,:,0])
new_image = Image.new('RGB', (width, height), (0,0,0))
new_mask = Image.new('RGB', (width, height), (0,0,0))
new_mask.paste(mask, position)
new_image.paste(image, (0,0))
new_image.paste(new_object, position, mask=mask)
A = np.array(new_image)
A = A[position[1]:position[1]+mask_width,position[0]:position[0]+mask_height]
A = cv2.GaussianBlur(A, (9,9),0)
new_image = np.array(new_image)
new_image[position[1]:position[1]+mask_width,position[0]:position[0]+mask_height]
new_image, new_mask = augment(
[IAAPerspective(p=1), Resize(p=1, height=input_size[0], width=input_size[1])],
np.array(new_image),
np.array(new_mask)
)
new_mask = Image.fromarray(new_mask).convert('L')
new_mask = np.array(new_mask)
new_mask = cv2.dilate(new_mask,(5,5),iterations = 3)
new_mask = cv2.morphologyEx(new_mask, cv2.MORPH_CLOSE, (4, 4), 5)
new_mask = cv2.erode(new_mask,(3, 3),iterations = 3)
return new_image, new_mask
def hard_transform():
transforms = [
ShiftScaleRotate(shift_limit=0.1,
scale_limit=0.1,
rotate_limit=15,
border_mode=cv2.BORDER_REFLECT,
p=0.5),
IAAPerspective(scale=(0.02, 0.05), p=0.3),
RandomBrightnessContrast(brightness_limit=0.2,
contrast_limit=0.2,
p=0.3),
RandomGamma(gamma_limit=(85, 115), p=0.3),
HueSaturationValue(p=0.3),
ChannelShuffle(p=0.5),
ToGray(p=0.2),
CLAHE(p=0.3),
RGBShift(p=0.3),
JpegCompression(quality_lower=50),
]
transforms = Compose(transforms)
return transforms
def strong_aug(p=0.8):
return Compose([
# RandomRotate90(),
# Flip(),
# Transpose(),
OneOf([
IAAAdditiveGaussianNoise(),
GaussNoise(),
], p=0.2),
OneOf([ #模糊
MotionBlur(p=0.5),
MedianBlur(blur_limit=3, p=0.5),
Blur(blur_limit=3, p=0.5),
JpegCompression(p=1,quality_lower=7,quality_upper=40)
], p=1),
# ShiftScaleRotate(shift_limit=0.0625, scale_limit=0.2, rotate_limit=45, p=0.2),
OneOf([
IAAPiecewiseAffine(p=1,scale=(0.005, 0.01), nb_rows=4, nb_cols=4),
IAAPerspective(p=1,scale=(random.uniform(0.01,0.03),random.uniform(0.01, 0.03))),
ElasticTransform(p=1,alpha=random.randint(50,100), sigma=random.randint(8,13), alpha_affine=0,border_mode=3),
], p=0.2),
OneOf([
ElasticTransform(p=1,alpha=random.randint(50,100), sigma=random.randint(8,13), alpha_affine=0,border_mode=3),
], p=0.6),
OneOf([
OpticalDistortion(p=1,distort_limit=0.2,border_mode=3),
# GridDistortion(p=1,distort_limit=0.1,border_mode=3),
], p=0.1),
OneOf([
CLAHE(clip_limit=2,p=0.5),
# IAASharpen(),
IAAEmboss(p=0.5),
RandomBrightnessContrast(p=1), #随机调整亮度饱和度，和下一个区别？
HueSaturationValue(p=1), #随机调整hsv值
RGBShift(p=0.5), #随机调整rgb值
ChannelShuffle(p=0.5), #RGB通道调换
InvertImg(p=0.1), #255-像素值，反转图像
], p=0.5),
], p=p)
def watermark_with_transparency(image, new_object, input_size):
width, height = image.size
mask_width, mask_height = new_object.size
position = random.randint(0,width - mask_width), random.randint(0,height - mask_height)
mask = new_object.point(thresh)
new_image = Image.new('L', (width, height))
new_mask = Image.new('L', (width, height))
new_mask.paste(mask, position)
new_image.paste(image, (0,0))
new_image.paste(new_object, position, mask=mask)
new_image, new_mask = augment(
[IAAPerspective(p=1), Resize(p=1, height=input_size[0], width=input_size[1])],
np.array(new_image),
np.array(new_mask)
)
return new_image, new_mask
def vanilla_transform(p):
return Compose([
HorizontalFlip(p=0.5),
VerticalFlip(p=0.5),
ShiftScaleRotate(rotate_limit=30,
scale_limit=0.15,
border_mode=cv2.BORDER_CONSTANT,
value=[0, 0, 0],
p=0.5),
IAAAdditiveGaussianNoise(p=0.2),
IAAPerspective(p=0.5),
OneOf(
[
CLAHE(p=1),
RandomBrightness(p=1),
RandomGamma(p=1),
],
p=0.5,
),
OneOf(
[
IAASharpen(p=1),
Blur(blur_limit=3, p=1),
MotionBlur(blur_limit=3, p=1),
],
p=0.5,
),
OneOf(
[
RandomContrast(p=1),
HueSaturationValue(p=1),
],
p=0.5,
),
],
p=p)
def aug_mega_hardcore(p=.95):
return Compose([
OneOf([CLAHE(clip_limit=2),
IAASharpen(p=.25),
IAAEmboss(p=.25)],
p=.35),
OneOf([
IAAAdditiveGaussianNoise(p=.3),
GaussNoise(p=.7),
], p=.5),
RandomRotate90(),
Flip(),
Transpose(),
OneOf([
MotionBlur(p=.2),
MedianBlur(blur_limit=3, p=.3),
Blur(blur_limit=3, p=.5),
],
p=.4),
OneOf([
RandomContrast(p=.5),
RandomBrightness(p=.5),
], p=.4),
ShiftScaleRotate(
shift_limit=.0, scale_limit=.45, rotate_limit=45, p=.7),
OneOf([
OpticalDistortion(p=0.3),
GridDistortion(p=0.2),
ElasticTransform(p=.2),
IAAPerspective(p=.2),
IAAPiecewiseAffine(p=.3),
],
p=.6),
HueSaturationValue(p=.5)
],
p=p)
def transform(image, mask, image_name, mask_name):
x, y = image, mask
rand = random.uniform(0, 1)
if (rand > 0.5):
images_name = [f"{image_name}"]
masks_name = [f"{mask_name}"]
images_aug = [x]
masks_aug = [y]
it = iter(images_name)
it2 = iter(images_aug)
imagedict = dict(zip(it, it2))
it = iter(masks_name)
it2 = iter(masks_aug)
masksdict = dict(zip(it, it2))
return imagedict, masksdict
mask_density = np.count_nonzero(y)
## Augmenting only images with Gloms
if (mask_density > 0):
try:
h, w, c = x.shape
except Exception as e:
image = image[:-1]
x, y = image, mask
h, w, c = x.shape
aug = Blur(p=1, blur_limit=3)
augmented = aug(image=x, mask=y)
x0 = augmented['image']
y0 = augmented['mask']
# aug = CenterCrop(p=1, height=32, width=32)
# augmented = aug(image=x, mask=y)
# x1 = augmented['image']
# y1 = augmented['mask']
## Horizontal Flip
aug = HorizontalFlip(p=1)
augmented = aug(image=x, mask=y)
x2 = augmented['image']
y2 = augmented['mask']
aug = VerticalFlip(p=1)
augmented = aug(image=x, mask=y)
x3 = augmented['image']
y3 = augmented['mask']
# aug = Normalize(p=1)
# augmented = aug(image=x, mask=y)
# x4 = augmented['image']
# y4 = augmented['mask']
aug = Transpose(p=1)
augmented = aug(image=x, mask=y)
x5 = augmented['image']
y5 = augmented['mask']
aug = RandomGamma(p=1)
augmented = aug(image=x, mask=y)
x6 = augmented['image']
y6 = augmented['mask']
## Optical Distortion
aug = OpticalDistortion(p=1, distort_limit=2, shift_limit=0.5)
augmented = aug(image=x, mask=y)
x7 = augmented['image']
y7 = augmented['mask']
## Grid Distortion
aug = GridDistortion(p=1)
augmented = aug(image=x, mask=y)
x8 = augmented['image']
y8 = augmented['mask']
aug = RandomGridShuffle(p=1)
augmented = aug(image=x, mask=y)
x9 = augmented['image']
y9 = augmented['mask']
aug = HueSaturationValue(p=1)
augmented = aug(image=x, mask=y)
x10 = augmented['image']
y10 = augmented['mask']
# aug = PadIfNeeded(p=1)
# augmented = aug(image=x, mask=y)
# x11 = augmented['image']
# y11 = augmented['mask']
aug = RGBShift(p=1)
augmented = aug(image=x, mask=y)
x12 = augmented['image']
y12 = augmented['mask']
## Random Brightness
aug = RandomBrightness(p=1)
augmented = aug(image=x, mask=y)
x13 = augmented['image']
y13 = augmented['mask']
## Random Contrast
aug = RandomContrast(p=1)
augmented = aug(image=x, mask=y)
x14 = augmented['image']
y14 = augmented['mask']
#aug = MotionBlur(p=1)
#augmented = aug(image=x, mask=y)
# x15 = augmented['image']
# y15 = augmented['mask']
aug = MedianBlur(p=1, blur_limit=5)
augmented = aug(image=x, mask=y)
x16 = augmented['image']
y16 = augmented['mask']
aug = GaussianBlur(p=1, blur_limit=3)
augmented = aug(image=x, mask=y)
x17 = augmented['image']
y17 = augmented['mask']
aug = GaussNoise(p=1)
augmented = aug(image=x, mask=y)
x18 = augmented['image']
y18 = augmented['mask']
aug = GlassBlur(p=1)
augmented = aug(image=x, mask=y)
x19 = augmented['image']
y19 = augmented['mask']
aug = CLAHE(clip_limit=1.0,
tile_grid_size=(8, 8),
always_apply=False,
p=1)
augmented = aug(image=x, mask=y)
x20 = augmented['image']
y20 = augmented['mask']
aug = ChannelShuffle(p=1)
augmented = aug(image=x, mask=y)
x21 = augmented['image']
y21 = augmented['mask']
aug = ToGray(p=1)
augmented = aug(image=x, mask=y)
x22 = augmented['image']
y22 = augmented['mask']
aug = ToSepia(p=1)
augmented = aug(image=x, mask=y)
x23 = augmented['image']
y23 = augmented['mask']
aug = JpegCompression(p=1)
augmented = aug(image=x, mask=y)
x24 = augmented['image']
y24 = augmented['mask']
aug = ImageCompression(p=1)
augmented = aug(image=x, mask=y)
x25 = augmented['image']
y25 = augmented['mask']
aug = Cutout(p=1)
augmented = aug(image=x, mask=y)
x26 = augmented['image']
y26 = augmented['mask']
# aug = CoarseDropout(p=1, max_holes=8, max_height=32, max_width=32)
# augmented = aug(image=x, mask=y)
# x27 = augmented['image']
# y27 = augmented['mask']
# aug = ToFloat(p=1)
# augmented = aug(image=x, mask=y)
# x28 = augmented['image']
# y28 = augmented['mask']
aug = FromFloat(p=1)
augmented = aug(image=x, mask=y)
x29 = augmented['image']
y29 = augmented['mask']
## Random Brightness and Contrast
aug = RandomBrightnessContrast(p=1)
augmented = aug(image=x, mask=y)
x30 = augmented['image']
y30 = augmented['mask']
aug = RandomSnow(p=1)
augmented = aug(image=x, mask=y)
x31 = augmented['image']
y31 = augmented['mask']
aug = RandomRain(p=1)
augmented = aug(image=x, mask=y)
x32 = augmented['image']
y32 = augmented['mask']
aug = RandomFog(p=1)
augmented = aug(image=x, mask=y)
x33 = augmented['image']
y33 = augmented['mask']
aug = RandomSunFlare(p=1)
augmented = aug(image=x, mask=y)
x34 = augmented['image']
y34 = augmented['mask']
aug = RandomShadow(p=1)
augmented = aug(image=x, mask=y)
x35 = augmented['image']
y35 = augmented['mask']
aug = Lambda(p=1)
augmented = aug(image=x, mask=y)
x36 = augmented['image']
y36 = augmented['mask']
aug = ChannelDropout(p=1)
augmented = aug(image=x, mask=y)
x37 = augmented['image']
y37 = augmented['mask']
aug = ISONoise(p=1)
augmented = aug(image=x, mask=y)
x38 = augmented['image']
y38 = augmented['mask']
aug = Solarize(p=1)
augmented = aug(image=x, mask=y)
x39 = augmented['image']
y39 = augmented['mask']
aug = Equalize(p=1)
augmented = aug(image=x, mask=y)
x40 = augmented['image']
y40 = augmented['mask']
aug = Posterize(p=1)
augmented = aug(image=x, mask=y)
x41 = augmented['image']
y41 = augmented['mask']
aug = Downscale(p=1)
augmented = aug(image=x, mask=y)
x42 = augmented['image']
y42 = augmented['mask']
aug = MultiplicativeNoise(p=1)
augmented = aug(image=x, mask=y)
x43 = augmented['image']
y43 = augmented['mask']
aug = FancyPCA(p=1)
augmented = aug(image=x, mask=y)
x44 = augmented['image']
y44 = augmented['mask']
# aug = MaskDropout(p=1)
# augmented = aug(image=x, mask=y)
# x45 = augmented['image']
# y45 = augmented['mask']
aug = GridDropout(p=1)
augmented = aug(image=x, mask=y)
x46 = augmented['image']
y46 = augmented['mask']
aug = ColorJitter(p=1)
augmented = aug(image=x, mask=y)
x47 = augmented['image']
y47 = augmented['mask']
## ElasticTransform
aug = ElasticTransform(p=1,
alpha=120,
sigma=512 * 0.05,
alpha_affine=512 * 0.03)
augmented = aug(image=x, mask=y)
x50 = augmented['image']
y50 = augmented['mask']
aug = CropNonEmptyMaskIfExists(p=1, height=22, width=32)
augmented = aug(image=x, mask=y)
x51 = augmented['image']
y51 = augmented['mask']
aug = IAAAffine(p=1)
augmented = aug(image=x, mask=y)
x52 = augmented['image']
y52 = augmented['mask']
# aug = IAACropAndPad(p=1)
# augmented = aug(image=x, mask=y)
# x53 = augmented['image']
# y53 = augmented['mask']
aug = IAAFliplr(p=1)
augmented = aug(image=x, mask=y)
x54 = augmented['image']
y54 = augmented['mask']
aug = IAAFlipud(p=1)
augmented = aug(image=x, mask=y)
x55 = augmented['image']
y55 = augmented['mask']
aug = IAAPerspective(p=1)
augmented = aug(image=x, mask=y)
x56 = augmented['image']
y56 = augmented['mask']
aug = IAAPiecewiseAffine(p=1)
augmented = aug(image=x, mask=y)
x57 = augmented['image']
y57 = augmented['mask']
aug = LongestMaxSize(p=1)
augmented = aug(image=x, mask=y)
x58 = augmented['image']
y58 = augmented['mask']
aug = NoOp(p=1)
augmented = aug(image=x, mask=y)
x59 = augmented['image']
y59 = augmented['mask']
# aug = RandomCrop(p=1, height=22, width=22)
# augmented = aug(image=x, mask=y)
# x61 = augmented['image']
# y61 = augmented['mask']
# aug = RandomResizedCrop(p=1, height=22, width=20)
# augmented = aug(image=x, mask=y)
# x63 = augmented['image']
# y63 = augmented['mask']
aug = RandomScale(p=1)
augmented = aug(image=x, mask=y)
x64 = augmented['image']
y64 = augmented['mask']
# aug = RandomSizedCrop(p=1, height=22, width=20, min_max_height = [32,32])
# augmented = aug(image=x, mask=y)
# x66 = augmented['image']
# y66 = augmented['mask']
# aug = Resize(p=1, height=22, width=20)
# augmented = aug(image=x, mask=y)
# x67 = augmented['image']
# y67 = augmented['mask']
aug = Rotate(p=1)
augmented = aug(image=x, mask=y)
x68 = augmented['image']
y68 = augmented['mask']
aug = ShiftScaleRotate(p=1)
augmented = aug(image=x, mask=y)
x69 = augmented['image']
y69 = augmented['mask']
aug = SmallestMaxSize(p=1)
augmented = aug(image=x, mask=y)
x70 = augmented['image']
y70 = augmented['mask']
images_aug.extend([
x, x0, x2, x3, x5, x6, x7, x8, x9, x10, x12, x13, x14, x16, x17,
x18, x19, x20, x21, x22, x23, x24, x25, x26, x29, x30, x31, x32,
x33, x34, x35, x36, x37, x38, x39, x40, x41, x42, x43, x44, x46,
x47, x50, x51, x52, x54, x55, x56, x57, x58, x59, x64, x68, x69,
x70
])
masks_aug.extend([
y, y0, y2, y3, y5, y6, y7, y8, y9, y10, y12, y13, y14, y16, y17,
y18, y19, y20, y21, y22, y23, y24, y25, y26, y29, y30, y31, y32,
y33, y34, y35, y36, y37, y38, y39, y40, y41, y42, y43, y44, y46,
y47, y50, y51, y52, y54, y55, y56, y57, y58, y59, y64, y68, y69,
y70
])
idx = -1
images_name = []
masks_name = []
for i, m in zip(images_aug, masks_aug):
if idx == -1:
tmp_image_name = f"{image_name}"
tmp_mask_name = f"{mask_name}"
else:
tmp_image_name = f"{image_name}_{smalllist[idx]}"
tmp_mask_name = f"{mask_name}_{smalllist[idx]}"
images_name.extend(tmp_image_name)
masks_name.extend(tmp_mask_name)
idx += 1
it = iter(images_name)
it2 = iter(images_aug)
imagedict = dict(zip(it, it2))
it = iter(masks_name)
it2 = iter(masks_aug)
masksdict = dict(zip(it, it2))
return imagedict, masksdict
train_df = train_df.append(holdout)
print('train_df.shape:', train_df.shape)
nunique = list(train_df.nunique())[1:-2]
print('nunique:', nunique)
# --- IMAGE DATABUNCH ---
if not config['FINETUNE']:
train_tf = Compose([
OneOf([
ShiftScaleRotate(shift_limit=0.0625,
scale_limit=0.1,
rotate_limit=15,
always_apply=True),
IAAPerspective(always_apply=True),
IAAPiecewiseAffine(always_apply=True)
],
p=0.5)
])
def new_open_image(fn: PathOrStr,
div: bool = True,
convert_mode: str = 'L',
after_open: Callable = None,
transforms=True) -> Image:
"Return `Image` object created from image in file `fn`."
with warnings.catch_warnings():
warnings.simplefilter("ignore",
UserWarning) # EXIF warning from TiffPlugin
x = PIL.Image.open(fn).convert(convert_mode)
def compose_augmentations(img_height,
img_width,
flip_p=0.5,
translate_p=0.5,
distort_p=0.5,
color_p=0.5,
overlays_p=0.15,
blur_p=0.25,
noise_p=0.25):
# Resize
resize_p = 1 if img_height != 1024 else 0
# Random sized crop
if img_height == 1024:
min_max_height = (896, 960)
elif img_height == 512:
min_max_height = (448, 480)
elif img_height == 256:
min_max_height = (224, 240)
else:
raise NotImplementedError
return Compose([
Resize(p=resize_p, height=img_height, width=img_width),
OneOf([
HorizontalFlip(p=0.5),
VerticalFlip(p=0.5),
Transpose(p=0.5),
RandomRotate90(p=0.5),
],
p=flip_p),
OneOf([
Rotate(p=0.25, limit=10),
RandomSizedCrop(p=0.5,
min_max_height=min_max_height,
height=img_height,
width=img_width),
OneOrOther(IAAAffine(p=0.1, translate_percent=0.05),
IAAPerspective(p=0.1)),
],
p=translate_p),
OneOf([
ElasticTransform(p=0.5,
alpha=10,
sigma=img_height * 0.05,
alpha_affine=img_height * 0.03,
approximate=True),
GridDistortion(p=0.5),
OpticalDistortion(p=0.5),
IAAPiecewiseAffine(p=0.25, scale=(0.01, 0.03)),
],
p=distort_p),
OneOrOther(
OneOf([
CLAHE(p=0.5),
RandomGamma(p=0.5),
RandomContrast(p=0.5),
RandomBrightness(p=0.5),
RandomBrightnessContrast(p=0.5),
],
p=color_p),
OneOf([IAAEmboss(p=0.1),
IAASharpen(p=0.1),
IAASuperpixels(p=0)],
p=overlays_p)),
OneOrOther(
OneOf([
Blur(p=0.2),
MedianBlur(p=0.1),
MotionBlur(p=0.1),
GaussianBlur(p=0.1),
],
p=blur_p),
OneOf([GaussNoise(p=0.2),
IAAAdditiveGaussianNoise(p=0.1)],
p=noise_p)),
Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
ToTensor(sigmoid=False),
])
def do_augmentation(dataset_dir, output_dir, file_ext, strAugs):
print("hi")
for indDataset in dataset_dir:
files_list = os.listdir(indDataset)
imagesList = filterImages(files_list, file_ext)
for augstr in strAugs:
for image_name in imagesList:
try:
base_name = os.path.splitext(image_name)[0]
image = cv2.imread(indDataset + image_name)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
tree = ET.parse(indDataset + base_name + ".xml")
root = tree.getroot()
bbox = []
label = []
idx = 0
xminxml = []
yminxml = []
xmaxxml = []
ymaxxml = [
] # save to a new array to prevent out of order access
for xmin in root.iter('xmin'):
bbox.append([int(float(xmin.text))])
xminxml.append(xmin)
for ymin in root.iter('ymin'):
bbox[idx].append(int(float(ymin.text)))
idx += 1
yminxml.append(ymin)
idx = 0
for xmax in root.iter('xmax'):
bbox[idx].append(int(float(xmax.text)))
idx += 1
xmaxxml.append(xmax)
idx = 0
for ymax in root.iter('ymax'):
bbox[idx].append(int(float(ymax.text)))
idx += 1
ymaxxml.append(ymax)
idx = 0
for name in root.iter('name'):
label.append(name.text)
idx += 1
height, width, channels = image.shape
annotations = {
'image': image.copy(),
'bboxes': bbox,
'category_id': label
}
# category_id_to_name = {'car': 'car', 'tree': 'tree', 'house': 'house', 'pool':'pool'}
# category_id_to_name = {'car': 'car', 'truck': 'truck', 'bike': 'bike'}
category_id_to_name = {'cigarette': 'cigarette'}
# classNames = {1: 'parking sign',
# 2: 'stop sign',
# 3: 'tunnel sign',}
# visualize(annotations, category_id_to_name)
# plt.show()
###augment the image
###random crop
aug = get_aug([
HorizontalFlip(p=0.5),
# RandomSizedBBoxSafeCrop(height=300, width=300, p=0.3),
RandomBrightnessContrast(brightness_limit=0.1,
contrast_limit=0.1,
p=0.3),
# RandomRain(blur_value=2, p=0.5),
RandomSunFlare(p=0.3, src_radius=50),
# Cutout(max_h_size=20, max_w_size=20, p=0.4),
IAAPerspective(scale=(0.1, 0.1), p=0.4),
# ShiftScaleRotate(scale_limit=0.2, border_mode=cv2.BORDER_CONSTANT, p=1.0),
# RandomScale(p=0.3),
# Rotate(p=0.3, border_mode=cv2.BORDER_CONSTANT, limit=30),
# RandomGamma(p=1.0),
IAAPiecewiseAffine(scale=(0.01, 0.01), p=0.4)
])
#
# aug = get_aug([HorizontalFlip(p=1)])
augmented = aug(**annotations)
# print(augmented)
# visualize(augmented, category_id_to_name)
# plt.show()
# print(augmented)
if augmented["bboxes"] == []:
continue # if it could not generate labels
print(len(augmented["bboxes"]))
idx = 0
for xmin in xminxml:
xmin.text = str(int(augmented['bboxes'][idx][0]))
idx += 1
idx = 0
for ymin in yminxml:
ymin.text = str(int(augmented['bboxes'][idx][1]))
idx += 1
idx = 0
for xmax in xmaxxml:
xmax.text = str(int(augmented['bboxes'][idx][2]))
idx += 1
idx = 0
for ymax in ymaxxml:
ymax.text = str(int(augmented['bboxes'][idx][3]))
idx += 1
for fileName in root.iter('filename'):
fileName.text = base_name + augstr + file_ext
# plt.show()
# write to file
tree.write(output_dir + base_name + augstr + ".xml")
image = cv2.cvtColor(augmented['image'], cv2.COLOR_RGB2BGR)
cv2.imwrite(output_dir + base_name + augstr + file_ext,
image)
print("saved image ", base_name + augstr + file_ext)
except Exception as e:
print(e)
print("Exception: ", augmented)
# cv2.imshow("augmented", augmented["image"])
# cv2.waitKey(0)
#
##Create validation file###
# create_validation_file(output_dir)
# print("Created Validation Files")
#
print("copying original")
###Copy original into source directory
for folder in dataset_dir:
filenames = os.listdir(folder)
print(filenames)
for name in filenames:
print("in: ", folder + name)
print("out: ", output_dir + name)
print("name:", name)
shutil.copy(folder + name, output_dir + name)
print("moved: " + name)
print("Done")
import numpy as np
import cv2
from matplotlib import pyplot as plt
from albumentations import (HorizontalFlip, IAAPerspective, ShiftScaleRotate, CLAHE, RandomRotate90,
Transpose, Blur, OpticalDistortion, GridDistortion, HueSaturationValue,
IAAAdditiveGaussianNoise, GaussNoise, MotionBlur, MedianBlur, IAAPiecewiseAffine,
IAASharpen, IAAEmboss, RandomBrightnessContrast, Flip, OneOf, Compose)
image = cv2.imread("test.jpg", 1) # BGR
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
aug = HorizontalFlip(p=1)
img_horizontalflip = aug(image=image)['image']
aug = IAAPerspective(p=1)
img_IAAPerspective = aug(image=image)['image']
aug = ShiftScaleRotate(p=1)
img_ShiftScaleRotate = aug(image=image)['image']
aug = GaussNoise(var_limit=10, p=1)
img_gaussNoise = aug(image=image)['image']
def strong_aug(p=.5):
return Compose([
RandomRotate90(),
Flip(),
Transpose(),
OneOf([
IAAAdditiveGaussianNoise(),
GaussNoise(),
], p=.2),
OneOf([
def apply_image_augmentation(augmentator, image):
augmented_image = augmentator(image=image)["image"]
return augmented_image
def horizontal_stack_images(image_1, image_2):
return np.hstack((image_1, image_2))
if __name__ == "__main__":
print("[INFO] Augmentation example, press 'q' to finish the example")
# Instancia o objeto de augmentação
augmentator = Compose([
Rotate(15),
Blur(5),
IAAPerspective(scale=(0.025, 0.05), p=0.8),
RandomBrightnessContrast(brightness_limit=0.35, contrast_limit=0.35)
],
p=0.7)
dataset, (characters_images,
characters_labels) = read_hdf5_dataset("characters_dataset.hdf5")
for idx, image in enumerate(characters_images):
augmented_image = apply_image_augmentation(augmentator, image)
cv2.imshow("Character x Augmented character",
horizontal_stack_images(image, augmented_image))
print("[INFO] Label => ", characters_labels[idx])
key = cv2.waitKey(0) & 0xff
if key == ord('q'):
# %%
# Image Compression
aug = ImageCompression(quality_lower=50, quality_upper=50)
image8 = (image * 256).astype("uint8")
augmented = aug(image=image8, mask=mask)
image_scaled = augmented["image"]
mask_scaled = augmented["mask"]
visualize(image_scaled, mask_scaled, original_image=image8, original_mask=mask)
# %%
# IAAPerspective
aug = IAAPerspective()
image8 = (image * 256).astype("uint8")
mask8 = mask.astype("uint8")
augmented = aug(image=image8, mask=mask8)
image_scaled = augmented["image"]
mask_scaled = augmented["mask"]
visualize(
image_scaled, mask_scaled, original_image=image8, original_mask=mask8
)
# %%
# MultiplicativeNoise
aug = MultiplicativeNoise(multiplier=(0.8, 1.2))
def perspective(image, mask):
aug = IAAPerspective(p=1.)
augmented = aug(image=image, mask=mask)
return augmented['image'], augmented['mask']
def IAAP(self, image, scale=0.2, p=1):
image = image.astype(np.uint8)
aug = IAAPerspective(scale=scale, p=p)
output = aug(image=image)['image']
return output.astype(np.float32)