def __init__(
self,
prob=0.7,
blur_prob=0.7,
jitter_prob=0.7,
rotate_prob=0.7,
flip_prob=0.7,
):
super().__init__()
self.prob = prob
self.blur_prob = blur_prob
self.jitter_prob = jitter_prob
self.rotate_prob = rotate_prob
self.flip_prob = flip_prob
self.transforms = al.Compose(
[
transforms.RandomRotate90(),
transforms.Flip(),
transforms.HueSaturationValue(),
transforms.RandomBrightnessContrast(),
transforms.Transpose(),
OneOf([
transforms.RandomCrop(220, 220, p=0.5),
transforms.CenterCrop(220, 220, p=0.5)
],
p=0.5),
# transforms.Resize(352,352),
# transforms.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
],
p=self.prob)
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_augumentation(phase, width=512, height=512, min_area=0., min_visibility=0., ft='coco'):
# from albumentations for all detection and segmentation
list_transforms = []
if phase == 'train':
list_transforms.extend([
transforms.LongestMaxSize(
max_size=width, always_apply=True),
albu.PadIfNeeded(min_height=height, min_width=width,
always_apply=True, border_mode=0, value=[0, 0, 0]),
transforms.RandomResizedCrop(
height=height,
width=width, p=0.3),
transforms.Flip(),
transforms.Transpose(),
albu.OneOf([
albu.RandomBrightnessContrast(brightness_limit=0.5,
contrast_limit=0.4),
albu.RandomGamma(gamma_limit=(50, 150)),
albu.NoOp()
]),
albu.OneOf([
albu.RGBShift(r_shift_limit=20, b_shift_limit=15,
g_shift_limit=15),
albu.HueSaturationValue(hue_shift_limit=5,
sat_shift_limit=5),
albu.NoOp()
]),
albu.CLAHE(p=0.8),
albu.HorizontalFlip(p=0.5),
albu.VerticalFlip(p=0.5),
])
if phase == 'test':
list_transforms.extend([
albu.Resize(height=height, width=width)
])
list_transforms.extend([
albu.Normalize(mean=(0.485, 0.456, 0.406),
std=(0.229, 0.224, 0.225), p=1),
ToTensorV2()
])
if phase == 'test':
return albu.Compose(list_transforms)
return albu.Compose(list_transforms, bbox_params=albu.BboxParams(format=ft,
min_area=min_area,
min_visibility=min_visibility,
label_fields=['category_id']))
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_valid_transforms():
return A.Compose([
transforms.Transpose(),
transforms.PadIfNeeded(600, 800),
rotate.Rotate(interpolation=cv2.INTER_LANCZOS4, p = 0.90),
crops.RandomResizedCrop(
TARGET_SIZE_VALID, TARGET_SIZE_VALID,
scale=(.75, 1),
interpolation=cv2.INTER_CUBIC,
p=1.0),
transforms.Flip(),
#transforms.RandomToneCurve(scale=.1),
#transforms.RandomBrightnessContrast(brightness_limit=0.0, contrast_limit=0.3, p=.7),
#transforms.HueSaturationValue(hue_shift_limit=10,
# sat_shift_limit=10,
# val_shift_limit=5, p=0.6),
transforms.Normalize(),
ToTensorV2()
])
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 augmentation(in_path='./train/raw_images/',
out_path='./train/aug_images/'):
for filename in os.listdir(in_path):
hf = transforms.HorizontalFlip(always_apply=True)
vf = transforms.VerticalFlip(always_apply=True)
tp = transforms.Transpose(always_apply=True)
rt = transforms.Rotate(limit=80, always_apply=True)
image = np.array(Image.open(in_path + filename))
hf_image = hf(image=image)['image']
vf_image = vf(image=image)['image']
tp_image = tp(image=image)['image']
rt_image = rt(image=image)['image']
count = 1
for img in [image, hf_image, vf_image, tp_image, rt_image]:
if len(img.shape) == 2:
img = Image.fromarray(img)
img.convert(mode='RGB')
else:
img = Image.fromarray(img, mode='RGB')
img.save(out_path +
filename.replace('.jpg', '_' + str(count) + '.jpg'))
count += 1
def __init__(
self,
prob=0,
Flip_prob=0,
HueSaturationValue_prob=0,
RandomBrightnessContrast_prob=0,
crop_prob=0,
randomrotate90_prob=0,
elastictransform_prob=0,
gridistortion_prob=0,
opticaldistortion_prob=0,
verticalflip_prob=0,
horizontalflip_prob=0,
randomgamma_prob=0,
CoarseDropout_prob=0,
RGBShift_prob=0,
MotionBlur_prob=0,
MedianBlur_prob=0,
GaussianBlur_prob=0,
GaussNoise_prob=0,
ChannelShuffle_prob=0,
ColorJitter_prob=0,
):
super().__init__()
self.prob = prob
self.randomrotate90_prob = randomrotate90_prob
self.elastictransform_prob = elastictransform_prob
self.transforms = al.Compose(
[
transforms.RandomRotate90(p=randomrotate90_prob),
transforms.Flip(p=Flip_prob),
transforms.HueSaturationValue(p=HueSaturationValue_prob),
transforms.RandomBrightnessContrast(
p=RandomBrightnessContrast_prob),
transforms.Transpose(),
OneOf(
[
transforms.RandomCrop(220, 220, p=0.5),
transforms.CenterCrop(220, 220, p=0.5),
],
p=crop_prob,
),
ElasticTransform(
p=elastictransform_prob,
alpha=120,
sigma=120 * 0.05,
alpha_affine=120 * 0.03,
),
GridDistortion(p=gridistortion_prob),
OpticalDistortion(p=opticaldistortion_prob,
distort_limit=2,
shift_limit=0.5),
VerticalFlip(p=verticalflip_prob),
HorizontalFlip(p=horizontalflip_prob),
RandomGamma(p=randomgamma_prob),
RGBShift(p=RGBShift_prob),
MotionBlur(p=MotionBlur_prob, blur_limit=7),
MedianBlur(p=MedianBlur_prob, blur_limit=9),
GaussianBlur(p=GaussianBlur_prob, blur_limit=9),
GaussNoise(p=GaussNoise_prob),
ChannelShuffle(p=ChannelShuffle_prob),
CoarseDropout(p=CoarseDropout_prob,
max_holes=8,
max_height=32,
max_width=32),
ColorJitter(p=ColorJitter_prob)
# transforms.Resize(352, 352),
# transforms.Normalize(
# mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)
# ),
],
p=self.prob,
)
train_img_paths = []
train_mask_paths = []
train_data_path = ["data/kvasir-seg/TrainDataset"]
for i in train_data_path:
train_img_paths.extend(glob(os.path.join(i, "images", "*")))
train_mask_paths.extend(glob(os.path.join(i, "masks", "*")))
train_img_paths.sort()
train_mask_paths.sort()
transforms = al.Compose(
[
transforms.RandomRotate90(),
transforms.Flip(),
transforms.HueSaturationValue(),
transforms.RandomBrightnessContrast(),
transforms.Transpose(),
OneOf(
[
transforms.RandomCrop(220, 220, p=0.5),
transforms.CenterCrop(220, 220, p=0.5),
],
p=1,
),
# transforms.Resize(352,352),
# transforms.Normalize(mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225)),
],
p=1,
)
dataset = KvasirDataset(train_img_paths,
train_mask_paths,
352,
