def get_transforms(*, data):
if data == 'train':
return Compose([
LongestMaxSize(CFG.size),
PadIfNeeded(min_height=CFG.size, min_width=CFG.size,
border_mode=1),
# Resize(CFG.size,CFG.size),
Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
),
ToTensorV2(),
])
elif data == 'valid':
return Compose([
LongestMaxSize(CFG.size),
PadIfNeeded(min_height=CFG.size, min_width=CFG.size,
border_mode=1),
# Resize(CFG.size,CFG.size),
Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
),
ToTensorV2(),
])
def get_augmentations(IMG_SZ):
train_aug = Compose([
LongestMaxSize(IMG_SZ, p=1.0, always_apply=True),
ShiftScaleRotate(p=1.0,
border_mode=cv2.BORDER_CONSTANT,
rotate_limit=10),
])
val_aug = Compose([
LongestMaxSize(IMG_SZ, p=1.0, always_apply=True),
])
return train_aug, val_aug
def __init__(self, width, height):
self.aug = Compose([
LongestMaxSize(max_size=width if width > height else height),
PadIfNeeded(min_height=height,
min_width=width,
border_mode=cv2.BORDER_CONSTANT)
])
def __init__(self, data_root='data', split_file='', size=(256, 256), fold=0, resize=False):
self.data_root = data_root
pkl_data = pickle.load(open(split_file, 'rb'))
if fold == -1:
self.path_list = pkl_data[0]['train']
self.path_list.extend(pkl_data[0]['val'])
else:
self.path_list = pkl_data[fold]['train']
self.len = len(self.path_list)
if resize:
self.transforms = Compose([Resize(height=size[0], width=size[1], interpolation=cv2.INTER_NEAREST),
ShiftScaleRotate(shift_limit=0.1, scale_limit=0.2, rotate_limit=20, p=0.7,
border_mode=cv2.BORDER_CONSTANT, value=0),
HorizontalFlip(p=0.5),
OneOf([ElasticTransform(p=1, alpha=50, sigma=30, alpha_affine=30,
border_mode=cv2.BORDER_CONSTANT, value=0),
OpticalDistortion(p=1, distort_limit=0.5, shift_limit=0.1,
border_mode=cv2.BORDER_CONSTANT, value=0)], p=0.5),
RandomGamma(gamma_limit=(80, 120), p=0.5),
GaussNoise(var_limit=(0.02, 0.1), mean=0, p=0.5)
])
else:
self.transforms = Compose([LongestMaxSize(max_size=max(size)),
PadIfNeeded(min_height=size[0], min_width=size[1], value=0,
border_mode=cv2.BORDER_CONSTANT),
ShiftScaleRotate(shift_limit=0.1, scale_limit=0.2, rotate_limit=20, p=0.7,
border_mode=cv2.BORDER_CONSTANT, value=0),
HorizontalFlip(p=0.5),
OneOf([ElasticTransform(p=1, alpha=50, sigma=30, alpha_affine=30,
border_mode=cv2.BORDER_CONSTANT, value=0),
OpticalDistortion(p=1, distort_limit=0.5, shift_limit=0.1,
border_mode=cv2.BORDER_CONSTANT, value=0)], p=0.5),
RandomGamma(gamma_limit=(80, 120), p=0.5),
GaussNoise(var_limit=(0.02, 0.1), mean=0, p=0.5)
])
def resize_transforms(image_size=224):
pre_size = int(image_size * 1.5)
random_crop = Compose([
SmallestMaxSize(pre_size, p=1),
RandomCrop(
image_size, image_size, p=1
)
])
resize = Compose([
Resize(image_size, image_size, p=1)
])
random_crop_big = Compose([
LongestMaxSize(pre_size, p=1),
RandomCrop(
image_size, image_size, p=1
)
])
# Converts the image to a square of size image_size x image_size
result = [
OneOf([
random_crop,
resize,
random_crop_big
], p=1)
]
return result
def valid_transform(image_size=224):
transforms = [
LongestMaxSize(max_size=image_size),
PadIfNeeded(image_size, image_size, border_mode=cv2.BORDER_CONSTANT),
post_transform()
]
transforms = Compose(transforms)
return transforms
def get_pred_label(image, solver, crop_size, stay_size, mode):
'''
params: 要求crop_size与stay_size为同奇偶
img_path: 测试图片的路径
crop_size: 图片太大需要裁切的大小；为一个整数c，代表(c,c)区域。
stay_size: 最终保存结果的size，是crop_size的中间部分；为一个整数s，代表(s,s)区域
'''
pad_sts_row = int(stay_size - image.shape[0] % stay_size)
pad_sts_column = int(stay_size - image.shape[1] % stay_size)
pad_cs_row = (crop_size - stay_size) // 2
pad_cs_column = (crop_size - stay_size) // 2
pad = ((pad_cs_row, pad_sts_row + pad_cs_row),
(pad_cs_column, pad_sts_column + pad_cs_column), (0, 0))
pad_img = np.pad(image, pad, mode='reflect')
pred_label = np.zeros(shape=(image.shape[0] + pad_sts_row,
image.shape[1] + pad_sts_column))
# predict and get the label
for row_idx in range(0, pad_img.shape[0], stay_size):
if row_idx > pad_img.shape[0] - crop_size:
break
for column_idx in range(0, pad_img.shape[1], stay_size):
if column_idx > pad_img.shape[1] - crop_size:
break
crop_img = pad_img[row_idx:row_idx + crop_size,
column_idx:column_idx + crop_size, :]
if mode == 'gray':
resize_img = LongestMaxSize(512)(image=crop_img)['image']
crop_result = solver.test_one_img_from_path(resize_img)
crop_mask = LongestMaxSize(256)(
image=crop_result)['image'] #这里是mask的resize
# crop_mask[crop_mask > 0.45] = 1.0
# crop_mask[crop_mask <= 0.45] = 0.0
elif mode == 'rgb':
crop_mask = solver.test_one_img_from_path(crop_img)
# crop_mask[crop_mask > 0.5] = 1.0
# crop_mask[crop_mask <= 0.5] = 0.0
pred_label[row_idx:row_idx + stay_size, column_idx:column_idx +
stay_size] = crop_mask[pad_cs_row:pad_cs_row +
stay_size,
pad_cs_column:pad_cs_column +
stay_size]
final_pred = pred_label[:image.shape[0], :image.shape[1]]
return final_pred
def aug_validation(prob=1.0, img_size=224):
return Compose([
LongestMaxSize(max_size=img_size),
PadIfNeeded(min_height=img_size,
min_width=img_size,
border_mode=cv2.BORDER_CONSTANT),
],
p=prob)
def pre_transforms(image_size=224):
return Compose(
[
LongestMaxSize(max_size=image_size),
PadIfNeeded(
image_size, image_size, border_mode=cv2.BORDER_CONSTANT
),
]
)
def pre_transforms(image_size: int = 256):
"""Transforms that always be applied before other transformations"""
transforms = Compose([
ImageToRGB(),
LongestMaxSize(max_size=image_size),
PadIfNeeded(
image_size, image_size, border_mode=cv2.BORDER_CONSTANT
),
])
return transforms
def __init__(self, width, height):
self.aug = Compose([
LongestMaxSize(max_size=width if width > height else height),
PadIfNeeded(min_height=height,
min_width=width,
border_mode=cv2.BORDER_CONSTANT)
],
keypoint_params=KeypointParams(
format='xy',
label_fields=['pose_id', "join_id"],
remove_invisible=True))
def load(self, path='/model'):
self.transform = Compose([
LongestMaxSize(max_size=224),
PadIfNeeded(224, 224, border_mode=cv2.BORDER_CONSTANT),
Normalize(),
ToTensor(),
])
self.model = torch.jit.load(os.path.join(path, 'model.pth'))
with open(os.path.join(path, 'tag2class.json')) as fin:
self.tag2class = json.load(fin)
self.class2tag = {v: k for k, v in self.tag2class.items()}
logging.debug(f'class2tag: {self.class2tag}')
def load(self, path="/model"):
self.transform = Compose([
LongestMaxSize(max_size=32),
PadIfNeeded(32, 32, border_mode=cv2.BORDER_CONSTANT),
Normalize(),
ToTensor(),
])
self.model = torch.jit.load(os.path.join(path, "model.pth"))
with open(os.path.join(path, "tag2class.json")) as fin:
self.tag2class = json.load(fin)
self.class2tag = {v: k for k, v in self.tag2class.items()}
logging.debug(f"class2tag: {self.class2tag}")
def __init__(self, data_root='data', split_file='', size=(256, 256), fold=0, resize=False):
self.data_root = data_root
pkl_data = pickle.load(open(split_file, 'rb'))
self.path_list = pkl_data[fold]['val']
self.len = len(self.path_list)
if resize:
self.transforms = Resize(height=size[0], width=size[1], interpolation=cv2.INTER_NEAREST)
else:
self.transforms = Compose([LongestMaxSize(max_size=max(size)),
PadIfNeeded(min_height=size[0], min_width=size[1], value=0,
border_mode=cv2.BORDER_CONSTANT)
])
def train_transform(image_size=224):
transforms = [
LongestMaxSize(max_size=image_size),
PadIfNeeded(image_size, image_size, border_mode=cv2.BORDER_CONSTANT),
ShiftScaleRotate(shift_limit=0.1,
scale_limit=0.1,
rotate_limit=45,
border_mode=cv2.BORDER_REFLECT,
p=0.5),
RandomRotate90(),
JpegCompression(quality_lower=50),
post_transform()
]
transforms = Compose(transforms)
return transforms
def load(self, path="/model"):
image_size = 512
self.transform = Compose([
LongestMaxSize(max_size=image_size),
PadIfNeeded(image_size,
image_size,
border_mode=cv2.BORDER_CONSTANT),
Normalize((0.485, 0.456, 0.406), (0.229, 0.224, 0.225),
always_apply=True),
ToTensor(),
])
self.model = torch.jit.load(os.path.join(path, "model.pth"))
with open(os.path.join(path, "tag2class.json")) as fin:
self.tag2class = json.load(fin)
self.class2tag = {v: k for k, v in self.tag2class.items()}
logging.debug(f"class2tag: {self.class2tag}")
def train_transform(
from_dicom: bool,
longest_max_size: int,
additional_transforms: List[BasicTransform] = None
) -> Compose:
additional_transforms = additional_transforms if additional_transforms is not None else []
initial_transforms = [
LongestMaxSize(longest_max_size),
]
if from_dicom:
initial_transforms.insert(0, Lambda(image=stack_channels_for_rgb))
final_transforms = [
ToFloat(),
ToTensorV2(),
]
transforms = initial_transforms + additional_transforms + final_transforms
return Compose(transforms, bbox_params=BboxParams(format='pascal_voc', label_fields=['labels']))
def __init__(self, width, height):
self.aug = Compose([
ShiftScaleRotate(p=0.5,
rotate_limit=5,
scale_limit=0.05,
border_mode=cv2.BORDER_CONSTANT),
ImageCompression(quality_lower=95, quality_upper=100, p=1),
IAAAffine(shear=0.2, always_apply=False, p=0.3),
LongestMaxSize(max_size=width if width > height else height),
PadIfNeeded(min_height=height,
min_width=width,
border_mode=cv2.BORDER_CONSTANT)
],
keypoint_params=KeypointParams(
format='xy',
label_fields=['pose_id', "join_id"],
remove_invisible=True))
def prepare(img,
boxes,
max_dim=None,
xflip=False,
gt_boxes=None,
gt_labels=None):
aug = get_aug([
LongestMaxSize(max_size=max_dim),
HorizontalFlip(p=float(xflip)),
ToTensor(normalize=dict(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])),
])
augmented = aug(image=img,
bboxes=boxes,
gt_labels=np.full(len(boxes), fill_value=1))
augmented_gt = aug(image=img, bboxes=gt_boxes, gt_labels=gt_labels)
img = augmented["image"].numpy().astype(np.float32)
boxes = np.asarray(augmented["bboxes"]).astype(np.float32)
gt_boxes = np.asarray(augmented_gt["bboxes"]).astype(np.float32)
return img, boxes, gt_boxes
def __init__(self, to_tensor=True):
augs = [
LongestMaxSize(640),
PadIfNeeded(640, 640, cv.BORDER_CONSTANT, value=0),
#RandomSizedBBoxSafeCrop(height = 300,width = 300),
RandomBrightness(p=0.5),
RandomContrast(p=0.5),
#RandomSunFlare(p=0.5, flare_roi=(0, 0, 1, 0.5), angle_lower=0.5,src_radius= 150),
RandomShadow(p=0.5,
num_shadows_lower=1,
num_shadows_upper=1,
shadow_dimension=5,
shadow_roi=(0, 0.5, 1, 1)),
HorizontalFlip(p=0.5),
GaussianBlur(p=0.5),
]
self.transform = Compose(augs,
bbox_params={
"format": "albumentations",
"min_area": 0,
"min_visibility": 0.2,
'label_fields': ['category_id']
})
def __init__(self,
root_dirpath,
images_dirpath,
annotations_path,
L_classes_idx_filter,
support_set_size=10,
image_id_key="image_id",
category_id_key="category_id",
F_image_id_to_relative_path=None,
augmentation=True,
desired_size=280,
batch_size=12,
num_batch=1):
self.root_dirpath = root_dirpath
self.images_dirpath = images_dirpath
self.annotations_path = annotations_path
self.image_id_key = image_id_key
self.category_id_key = category_id_key
self.L_classes_idx_filter = L_classes_idx_filter
self.support_set_size = support_set_size
self.F_image_id_to_relative_path = F_image_id_to_relative_path
self.augmentation = augmentation
self.desired_size = desired_size
self.batch_size = batch_size
self.num_batch = num_batch
with open(self.annotations_path) as f:
self.D_instances = json.load(f)
self.L_annotations = self.D_instances['annotations']
self.L_categories = self.D_instances['categories']
# list of real class indices in COCO dataset
self.L_real_class_idx = [x['id'] for x in self.L_categories]
# zero-based class indices of COCO dataset (0-79)
self.L_class_idx = range(len(self.L_real_class_idx))
# dict to map real class indices to zero-based indices
self.D_real_class_idx_to_class_idx = {
real_class_idx: class_idx
for class_idx, real_class_idx in enumerate(self.L_real_class_idx)
}
# dict to map zero based indices to the relative annotations
self.D_class_to_annotations = self.Create_class_to_annotations_dict()
# filter zero-based class indices which have no annotations
self.L_not_empty_class_idx = [
class_idx for class_idx in self.L_class_idx
if len(self.D_class_to_annotations[class_idx]) > 0
]
# filter only specified class indices
self.L_filtered_class_idx = [
class_idx for class_idx in self.L_not_empty_class_idx
if class_idx in self.L_classes_idx_filter
]
bbox_params = BboxParams(format='coco',
label_fields=[self.category_id_key])
augmentation_transform = Compose([
VerticalFlip(p=0.5),
HorizontalFlip(p=0.5),
LongestMaxSize(max_size=600),
PadIfNeeded(min_height=710,
min_width=710,
border_mode=cv2.BORDER_CONSTANT),
Rotate(p=1.0,
limit=12,
interpolation=cv2.INTER_LINEAR,
border_mode=cv2.BORDER_CONSTANT),
Resize(height=desired_size, width=desired_size),
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
ToTensor()
],
bbox_params=bbox_params)
loading_transform = Compose([
LongestMaxSize(max_size=desired_size),
PadIfNeeded(min_height=desired_size,
min_width=desired_size,
border_mode=cv2.BORDER_CONSTANT),
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
ToTensor()
],
bbox_params=bbox_params)
self.transform = augmentation_transform if self.augmentation else loading_transform
def aug_resize(prob=1.0, img_size=224, interpolation=0): return Compose([ LongestMaxSize(max_size=img_size, interpolation=interpolation) ], p=prob)
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
def albumentations_transforms(
crop_size,
shorter_side,
low_scale,
high_scale,
img_mean,
img_std,
img_scale,
ignore_label,
num_stages,
dataset_type,
):
from albumentations import (
Normalize,
HorizontalFlip,
RandomRotate90, # my addition
RandomBrightnessContrast, # my addition
CLAHE, # my addition
RandomGamma, # my addition
ElasticTransform, # my addition
GridDistortion, # my addition
MotionBlur, # my addition
RandomCrop,
PadIfNeeded,
RandomScale,
LongestMaxSize,
SmallestMaxSize,
OneOf,
)
from albumentations.pytorch import ToTensorV2 as ToTensor
from densetorch.data import albumentations2densetorch
if dataset_type == "densetorch":
wrapper = albumentations2densetorch
elif dataset_type == "torchvision":
wrapper = albumentations2torchvision
else:
raise ValueError(f"Unknown dataset type: {dataset_type}")
common_transformations = [
Normalize(max_pixel_value=1.0 / img_scale, mean=img_mean, std=img_std),
ToTensor(),
]
train_transforms = []
for stage in range(num_stages):
train_transforms.append(
wrapper([
ChangeBackground("../backgrounds", p=0.5), # my addition
MotionBlur(p=0.5),
OneOf([
RandomScale(scale_limit=(low_scale[stage],
high_scale[stage])),
LongestMaxSize(max_size=shorter_side[stage]),
SmallestMaxSize(max_size=shorter_side[stage]),
]),
PadIfNeeded(
min_height=crop_size[stage],
min_width=crop_size[stage],
border_mode=cv2.BORDER_CONSTANT,
value=np.array(img_mean) / img_scale,
mask_value=ignore_label,
),
HorizontalFlip(p=0.5, ),
RandomRotate90(p=0.5),
RandomBrightnessContrast(
p=.8), # only applies to images, not masks
RandomGamma(p=0.8), # only applies to images
OneOf(
[
ElasticTransform(p=0.5,
alpha=120,
sigma=500 * 0.05,
alpha_affine=500 * 0.03),
GridDistortion(p=0.5),
# A.OpticalDistortion(distort_limit=1, shift_limit=0.5, p=1),
],
p=.5),
RandomCrop(
height=crop_size[stage],
width=crop_size[stage],
),
] + common_transformations))
val_transforms = wrapper(common_transformations)
return train_transforms, val_transforms
## Rotate
elif augmentation == 'rotate':
transform = Rotate(always_apply=True)
transformed_image = transform(image=image)['image']
elif augmentation == 'random_rotate90':
transform = RandomRotate90(always_apply=True)
transformed_image = transform(image=image)['image']
elif augmentation == 'transpose':
transform = Transpose(always_apply=True)
transformed_image = transform(image=image)['image']
## Size
elif augmentation == 'resize':
transform = Resize(always_apply=True, height=100, width=100)
transformed_image = transform(image=image)['image']
elif augmentation == 'longest_max_size':
transform = LongestMaxSize(always_apply=True)
transformed_image = transform(image=image)['image']
elif augmentation == 'smallest_max_size':
transform = SmallestMaxSize(always_apply=True)
transformed_image = transform(image=image)['image']
name, ext = image_name.split('.')
new_path = name + '_' + augmentation + '.' + ext
cv2.imwrite(new_path, transformed_image)
def albumentations_transforms(
crop_size,
shorter_side,
low_scale,
high_scale,
img_mean,
img_std,
img_scale,
ignore_label,
num_stages,
dataset_type,
):
from albumentations import (
Normalize,
HorizontalFlip,
RandomCrop,
PadIfNeeded,
RandomScale,
LongestMaxSize,
SmallestMaxSize,
OneOf,
)
from albumentations.pytorch import ToTensorV2 as ToTensor
from densetorch.data import albumentations2densetorch
if dataset_type == "densetorch":
wrapper = albumentations2densetorch
elif dataset_type == "torchvision":
wrapper = albumentations2torchvision
else:
raise ValueError(f"Unknown dataset type: {dataset_type}")
common_transformations = [
Normalize(max_pixel_value=1.0 / img_scale, mean=img_mean, std=img_std),
ToTensor(),
]
train_transforms = []
for stage in range(num_stages):
train_transforms.append(
wrapper(
[
OneOf(
[
RandomScale(
scale_limit=(low_scale[stage], high_scale[stage])
),
LongestMaxSize(max_size=shorter_side[stage]),
SmallestMaxSize(max_size=shorter_side[stage]),
]
),
PadIfNeeded(
min_height=crop_size[stage],
min_width=crop_size[stage],
border_mode=cv2.BORDER_CONSTANT,
value=np.array(img_mean) / img_scale,
mask_value=ignore_label,
),
HorizontalFlip(p=0.5,),
RandomCrop(height=crop_size[stage], width=crop_size[stage],),
]
+ common_transformations
)
)
val_transforms = wrapper(common_transformations)
return train_transforms, val_transforms
local_inner = io.imread(os.path.join(
data_root, dirname, 'pupil_edge_mask',
os.path.splitext(img_name)[0] + '.png'),
as_gray=True)
local_outer = io.imread(os.path.join(
data_root, dirname, 'iris_edge_mask',
os.path.splitext(img_name)[0] + '.png'),
as_gray=True)
_, local_inner = cv2.threshold(local_inner, 127, 1, 0)
_, local_outer = cv2.threshold(local_outer, 127, 1, 0)
original_shape = img.shape
if resize:
img = cv2.resize(img, (input_size[1], input_size[0]),
interpolation=cv2.INTER_NEAREST)
else:
transforms = LongestMaxSize(max_size=max(input_size))
img = transforms(image=img)['image']
transformed_shape = img.shape
img, pads = padding_2D(img)
iris_prediction = np.zeros(img.shape)
tta = 1
if args.TTA:
tta = 4
for t in range(tta):
if t == 0:
img_tta = img
elif t == 1:
img_tta = np.flip(img, axis=1)
elif t == 2:
img_tta = exposure.adjust_gamma(img, 1.2)
elif t == 3:
def __call__(self, data):
data = to_numpy(data)
img, label = data['image'], data['label']
is_3d = True if img.shape == 4 else False
max_size = max(self._output_size[0], self._output_size[1])
if self._type == 'train':
task = [
HorizontalFlip(p=0.5),
RandomBrightnessContrast(p=0.5),
RandomGamma(p=0.5),
GridDistortion(border_mode=cv2.BORDER_CONSTANT, p=0.5),
LongestMaxSize(max_size, p=1),
PadIfNeeded(self._output_size[0],
self._output_size[1],
cv2.BORDER_CONSTANT,
value=0,
p=1),
ShiftScaleRotate(shift_limit=0.2,
scale_limit=0.5,
rotate_limit=30,
border_mode=cv2.BORDER_CONSTANT,
value=0,
p=0.5)
]
else:
task = [
LongestMaxSize(max_size, p=1),
PadIfNeeded(self._output_size[0],
self._output_size[1],
cv2.BORDER_CONSTANT,
value=0,
p=1)
]
if self.use_roi:
assert 'roi' in data.keys() and len(data['roi']) is not 0
roi = data['roi']
min_y = 0
max_y = img.shape[0]
min_x = 0
max_x = img.shape[1]
min_x = max(min_x, roi['min_x'] - self._roi_error_range)
max_x = min(max_x, roi['max_x'] + self._roi_error_range)
min_y = max(min_y, roi['min_y'] - self._roi_error_range)
max_y = min(max_y, roi['max_y'] + self._roi_error_range)
crop = [Crop(min_x, min_y, max_x, max_y, p=1)]
task = crop + task
aug = Compose_albu(task)
if not is_3d:
aug_data = aug(image=img, mask=label)
data['image'], data['label'] = aug_data['image'], aug_data['mask']
else:
keys = {}
targets = {}
for i in range(1, img.shape[2]):
keys.update({f'image{i}': 'image'})
keys.update({f'mask{i}': 'mask'})
targets.update({f'image{i}': img[:, :, i]})
targets.update({f'mask{i}': label[:, :, i]})
aug.add_targets(keys)
targets.update({'image': img[:, :, 0]})
targets.update({'mask': label[:, :, 0]})
aug_data = aug(**targets)
imgs = [aug_data['image']]
labels = [aug_data['mask']]
for i in range(1, img.shape[2]):
imgs.append(aug_data[f'image{i}'])
labels.append(aug_data[f'mask{i}'])
img = np.stack(imgs, axis=-1)
label = np.stack(labels, axis=-1)
data['image'] = img
data['label'] = label
return data
def resize_longest(x):
return Compose([
LongestMaxSize(
x, always_apply=True, interpolation=cv2.INTER_CUBIC, p=1)
],
p=1)
import pandas as pd
import numpy as np
import os.path as osp
import cv2
from tqdm import tqdm
from albumentations import Compose, LongestMaxSize
IMAGE_DIR = '../../../data/cumc/images/cropped/'
coords = pd.read_csv('../../../data/cumc/train_with_splits.csv')
resize = Compose([LongestMaxSize(max_size=256)], p=1)
# Load in 1-by-1
pixel_mean = np.zeros(1)
pixel_std = np.zeros(1)
k = 1
for rownum in tqdm(range(len(coords)), total=len(coords)):
img = cv2.imread(osp.join(IMAGE_DIR, coords['imgfile'].iloc[rownum]), 0)
#x1, y1, x2, y2 = coords[['x1','y1','x2','y2']].iloc[rownum]
#img = img[y1:y2,x1:x2]
img = resize(image=img)['image']
img = img / 255.
pixels = img.reshape((-1, 1)) # img.shape[2]
for pixel in pixels:
diff = pixel - pixel_mean
pixel_mean = pixel_mean + diff / k
pixel_std = pixel_std + diff * (pixel - pixel_mean)
