def __init__(self, num_classes, input_size=None):
super(HSRInhandObjectsDataTransform, self).__init__()
random.seed(1000)
if input_size is not None:
height, width = input_size
self._train_transform_list.append(Resize(height, width))
self._val_transform_list.append(Resize(height, width))
self._train_transform_list = self._train_transform_list + [
HorizontalFlip(p=0.5),
Rotate(p=0.5, limit=(-15, 15)),
GaussNoise(p=0.5),
RandomBrightnessContrast(p=0.5),
RandomShadow(p=0.5),
Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
),
ToTensor(num_classes=num_classes),
]
self._val_transform_list = self._val_transform_list + [
Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225],
),
ToTensor(num_classes=num_classes),
]
self._initialize_transform_dict()
def __init__(self, to_tensor=True):
augs = [
RandomSizedBBoxSafeCrop(height=512, width=512),
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),
]
if to_tensor:
augs.append(
ToTensor(normalize={
"mean": [0.485, 0.456, 0.406],
"std": [0.229, 0.224, 0.225]
}))
self.transform = Compose(augs,
bbox_params={
"format": "albumentations",
"min_area": 0,
"min_visibility": 0.2,
'label_fields': ['category_id']
})
def strong_aug(p=0.5, crop_size=(512, 512)):
return Compose([
RandomResizedCrop(crop_size[0],
crop_size[1],
scale=(0.3, 1.0),
ratio=(0.75, 1.3),
interpolation=4,
p=1.0),
RandomRotate90(),
Flip(),
Transpose(),
OneOf([
IAAAdditiveGaussianNoise(),
GaussNoise(),
], p=0.8),
OneOf([
MotionBlur(p=0.5),
MedianBlur(blur_limit=3, p=0.5),
Blur(blur_limit=3, p=0.5),
],
p=0.3),
ShiftScaleRotate(
shift_limit=0.2, scale_limit=0.5, rotate_limit=180, p=0.8),
OneOf([
OpticalDistortion(p=0.5),
GridDistortion(p=0.5),
IAAPiecewiseAffine(p=0.5),
ElasticTransform(p=0.5),
],
p=0.3),
OneOf([
CLAHE(clip_limit=2),
IAASharpen(),
IAAEmboss(),
RandomBrightnessContrast(),
],
p=0.3),
OneOf([
GaussNoise(),
RandomRain(
p=0.2, brightness_coefficient=0.9, drop_width=1, blur_value=5),
RandomSnow(p=0.4,
brightness_coeff=0.5,
snow_point_lower=0.1,
snow_point_upper=0.3),
RandomShadow(p=0.2,
num_shadows_lower=1,
num_shadows_upper=1,
shadow_dimension=5,
shadow_roi=(0, 0.5, 1, 1)),
RandomFog(
p=0.5, fog_coef_lower=0.3, fog_coef_upper=0.5, alpha_coef=0.1)
],
p=0.3),
RGBShift(),
HueSaturationValue(p=0.9),
],
p=p)
def setUpClass(cls):
from cral.tracking import set_experiment
from cral.pipeline.core import ClassificationPipe
from cral.augmentations.engine import Classification as Classification_augmentor
zip_url = 'https://segmind-data.s3.ap-south-1.amazonaws.com/edge/data/classification/bikes_persons_dataset.zip'
path_to_zip_file = tf.keras.utils.get_file('bikes_persons_dataset.zip',
zip_url,
cache_dir='/tmp',
cache_subdir='',
extract=False)
directory_to_extract_to = '/tmp'
with zipfile.ZipFile(path_to_zip_file, 'r') as zip_ref:
zip_ref.extractall(directory_to_extract_to)
set_experiment('6f2c48d8-970a-4e28-a609-38088cab599a')
cls.new_pipe = ClassificationPipe()
cls.new_pipe.add_data(train_images_dir='/tmp/bikes_persons_dataset',
val_images_dir=None,
split=0.2)
cls.new_pipe.lock_data()
aug = [
OneOf([
RandomFog(
fog_coef_lower=1, fog_coef_upper=1, alpha_coef=0.05,
p=1.0),
RandomBrightnessContrast(
brightness_limit=0.2, contrast_limit=10.5, p=1.0),
RandomShadow(shadow_roi=(0, 0.5, 1, 1),
num_shadows_lower=1,
num_shadows_upper=2,
shadow_dimension=5,
p=0.5),
RandomSnow(),
RandomSunFlare()
],
p=0.2)
]
augmentor = Classification_augmentor(aug=aug)
cls.new_pipe.set_aug(augmentor)
cls.report_path = '/tmp/reports'
if os.path.isdir(cls.report_path) is False:
os.mkdir(cls.report_path)
def strong_aug(p=0.6):
return Compose([
RandomShadow(shadow_roi=(0, 0, 1, 1), p=0.75),
OneOf([MotionBlur(), GaussianBlur()]),
OneOf([ToGray(), ToSepia()]),
OneOf([
InvertImg(),
RandomBrightnessContrast(brightness_limit=0.75, p=0.75),
RandomGamma(),
HueSaturationValue()
],
p=0.75)
],
bbox_params=BboxParams("pascal_voc",
label_fields=["category_id"],
min_area=0.0,
min_visibility=0.0),
p=p)
def __init__(self):
self.random_brightness_contrast = RandomBrightnessContrast()
self.hue_saturation_value = HueSaturationValue()
self.random_gamma = RandomGamma()
self.clahe = CLAHE()
self.blur = Blur()
self.gauss_noise = GaussNoise()
self.channel_shuffle = ChannelShuffle()
self.rgb_shift = RGBShift()
self.channel_dropout = ChannelDropout()
self.random_fog = RandomFog(fog_coef_upper=0.4)
self.random_rain = RandomRain()
self.random_snow = RandomSnow()
self.random_shadow = RandomShadow()
self.random_sunflare = RandomSunFlare(angle_upper=0.2)
def train_transformations(prob=1.0):
return Compose([
PadIfNeeded(min_height=384,
min_width=1280,
border_mode=cv2.BORDER_CONSTANT,
value=(0, 0, 0),
always_apply=True),
OneOf([HorizontalFlip(p=0.5),
Rotate(limit=20, p=0.3)], p=0.5),
OneOf([
ToGray(p=0.3),
RandomBrightnessContrast(p=0.5),
CLAHE(p=0.5),
IAASharpen(p=0.45)
],
p=0.5),
RandomShadow(p=0.4),
HueSaturationValue(p=0.3),
Normalize(always_apply=True)
],
p=prob)
def augment_data(image, steering_angle):
h, w = image.shape[:2]
result_image = np.copy(image)
result_steering_angle = steering_angle
result_image, result_steering_angle = random_flip(result_image,
result_steering_angle)
# result_image, result_steering_angle = random_translate(result_image, result_steering_angle)
aug = Compose(
[
# GaussianBlur(blur_limit=5, p=0.5),
RandomBrightness(limit=0.1, p=0.5),
RandomContrast(limit=0.1, p=0.5),
# CLAHE(p=0.5),
# Equalize(p=0.5),
# RandomSnow(p=0.5),
# RandomRain(p=0.5),
# RandomFog(p=0.5),
# RandomSunFlare(p=0.5),
RandomShadow(p=0.5),
CoarseDropout(
max_holes=4,
max_height=h // 30,
max_width=w // 30,
min_holes=1,
min_height=h // 40,
min_width=w // 40,
p=0.5,
),
],
p=1,
)
result_image = aug(image=result_image)["image"]
return result_image, result_steering_angle
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 augmentation_hardcore(size_image, p=0.8):
'''
Only use for second model
About albumentation, p in compose mean the prob that all transform in Compose work
'''
return Compose([
Resize(size_image, size_image),
CenterCrop(height=200, width=200, p=0.5),
Cutout(),
RandomShadow(shadow_dimension=3),
OneOf([
Flip(),
VerticalFlip(),
HorizontalFlip(),
], p=0.5),
OneOf([
RandomRotate90(),
Transpose(),
], p=0.5),
OneOf([GaussNoise(), GaussianBlur(blur_limit=9),
Blur()], p=0.5),
OneOf([
HueSaturationValue(
hue_shift_limit=10, sat_shift_limit=25, val_shift_limit=20),
RGBShift(),
RandomBrightness(brightness_limit=0.4),
RandomContrast(),
RandomBrightnessContrast(),
],
p=0.5),
OneOf([ShiftScaleRotate(),
ElasticTransform(),
RandomGridShuffle()],
p=0.5)
],
p=p)
def __init__(self, num_classes, input_size):
super(TuSimpleDataTransform, self).__init__()
random.seed(1000)
height, width = input_size
self._train_transform_list = self._train_transform_list + [
HorizontalFlip(p=0.5),
GaussNoise(p=0.5),
RandomBrightnessContrast(p=0.5),
RandomShadow(p=0.5),
RandomRain(rain_type="drizzle", p=0.5),
ShiftScaleRotate(rotate_limit=10, p=0.5),
RandomResizedCrop(
height=height, width=width, scale=(0.8, 1), p=0.5),
]
self._train_transform_list.append(Resize(height, width))
self._val_transform_list.append(Resize(height, width))
self._train_transform_list.append(ToTensor(num_classes=num_classes))
self._val_transform_list.append(ToTensor(num_classes=num_classes))
self._initialize_transform_dict()
p=0.5),
ElasticTransform(p=0.5,
alpha=1,
sigma=50,
alpha_affine=0.2,
border_mode=cv2.BORDER_CONSTANT)
]),
OneOf([
CLAHE(),
Solarize(),
RandomBrightness(),
RandomContrast(limit=0.2),
RandomBrightnessContrast(),
]),
JpegCompression(quality_lower=20, quality_upper=100),
RandomShadow(num_shadows_lower=1, num_shadows_upper=2),
PadIfNeeded(min_height=64,
min_width=100,
border_mode=cv2.BORDER_CONSTANT,
p=0.5),
Cutout(num_holes=8, max_h_size=16, max_w_size=16),
InvertImg(p=0.3),
ToGray()
# GridDistortion(num_steps=10, distort_limit = (0, 0.1), border_mode = cv2.BORDER_CONSTANT)
# OneOf([
# GridDistortion(p=0.1),
# IAAPiecewiseAffine(p=0.3),
# ], p=1),
])
charset = open('../data/characters', 'r').read()
def __call__(self, image, boxes=None, labels=None):
image = RandomShadow(p=0.25)(image=image)['image']
return image.astype(np.float32), boxes, labels
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
elif augmentation == 'iso_noise':
transform = ISONoise(always_apply=True, color_shift=(0.08, 0.1),
intensity=(0.5, 0.8))
transformed_image = transform(image=image)['image']
elif augmentation == 'shot_noise':
transform = iaa.imgcorruptlike.ShotNoise(severity=2)
transformed_image = transform(image=image)
elif augmentation == 'speckle_noise':
transform = iaa.imgcorruptlike.SpeckleNoise(severity=2)
transformed_image = transform(image=image)
elif augmentation == 'random_shadow':
transform = RandomShadow(always_apply=True)
transformed_image = transform(image=image)['image']
elif augmentation == 'random_sun_flare':
transform = RandomSunFlare(always_apply=True)
transformed_image = transform(image=image)['image']
elif augmentation == 'spatter':
transform = iaa.imgcorruptlike.Spatter(severity=2)
transformed_image = transform(image=image)
## Edges
elif augmentation == 'canny':
transform = iaa.Canny(alpha=(0.0, 0.9))
transformed_image = transform(image=image)
def __init__(self, opt):
# super(Batch_Balanced_Dataset, self).__init__()
self.tbaug = TenBrightAug()
self.incbaug = IncBrightAug()
self.colaug = ColorAug()
self.distortaug = DistortAug()
self.grayimg = GrayImg()
self.binimg = BinImg()
self.jpgaug = JPEGAug(0.8)
self.resizeimg = ResizeAug(opt.imgW, opt.imgH)
self.resizeimg_test = ResizeAug(opt.imgW, opt.imgH, rand_scale=False)
l1 = len(opt.train_data.strip().split(','))
if l1 == 1:
self.batch_sizes = [int(opt.batch_size)]
elif l1 == 3:
self.batch_sizes = [
int(opt.batch_size * opt.batch_ratio),
opt.batch_size - int(opt.batch_size * opt.batch_ratio)
]
elif l1 == 4:
b1 = int(opt.batch_size * opt.batch_ratio2)
self.batch_sizes = [int(b1 * opt.batch_ratio), 0, 0]
self.batch_sizes[1] = b1 - self.batch_sizes[0]
self.batch_sizes[
2] = opt.batch_size - self.batch_sizes[0] - self.batch_sizes[1]
if not opt.alldata:
self.test_books = [
'200021660', '200005598', 'hnsd006', 'umgy003', '100249416',
'umgy011', 'umgy010'
]
else:
print('use all data')
self.test_books = [
# '200021660',
# '200005598',
'hnsd006',
'umgy003',
'100249416',
'umgy011',
'umgy010'
]
self.train_tf1 = transforms.Compose([
self.distortaug, self.colaug, self.tbaug, self.incbaug,
self.grayimg, self.binimg, self.tbaug, self.incbaug, self.jpgaug,
self.resizeimg,
transforms.ToTensor()
])
self.train_tf0 = transforms.Compose(
[self.grayimg, self.resizeimg,
transforms.ToTensor()])
self.train_tf00 = Compose([
OneOf([
OpticalDistortion(distort_limit=0.05,
shift_limit=10,
border_mode=cv2.BORDER_WRAP,
p=0.5),
ElasticTransform(p=0.5,
alpha=1,
sigma=50,
alpha_affine=0.2,
border_mode=cv2.BORDER_CONSTANT)
]),
OneOf([
CLAHE(),
Solarize(),
RandomBrightness(),
RandomContrast(limit=0.2),
RandomBrightnessContrast(),
]),
JpegCompression(quality_lower=20, quality_upper=100),
RandomShadow(num_shadows_lower=1, num_shadows_upper=2),
PadIfNeeded(min_height=64,
min_width=100,
border_mode=cv2.BORDER_CONSTANT,
p=0.5),
Cutout(num_holes=8, max_h_size=16, max_w_size=16),
InvertImg(p=0.3),
ToGray()
])
self.train_tf01 = Compose([
JpegCompression(quality_lower=20, quality_upper=100),
Cutout(num_holes=4, max_h_size=8, max_w_size=8),
InvertImg(p=0.3)
])
self.randtf = transforms.RandomApply([self.distortaug])
self.train_tf2 = transforms.Compose(
[self.resizeimg_test, transforms.ToTensor()])
self.data_loader_list = []
self.datasets = []
self.data_samplers = []
self.opt = opt
self.train_data = opt.train_data.strip().split(',')
if not 'txt' in self.train_data[0]:
self.datasets.append(
RealImageLMDB(self.train_data[0],
transform=self.train_tf0,
transform2=self.train_tf00,
testBooks=self.test_books,
character=opt.character,
max_batch_length=opt.batch_max_length))
else:
self.datasets.append(
RealImageTxtLMDB(self.train_data[0],
transform=self.train_tf0,
transform2=self.train_tf00,
testBooks=self.test_books,
max_batch_length=opt.batch_max_length))
if len(self.train_data) == 3:
self.datasets.append(
SynthImageLMDB(self.train_data[1],
self.train_data[2],
transform=self.train_tf2,
transform2=self.train_tf01,
size=(opt.imgH, opt.imgW),
gray_bin_ratio=0.5,
max_label_length=opt.batch_max_length))
if len(self.train_data) == 4:
self.datasets.append(
RealImageTxtLMDB(self.train_data[3],
transform=self.train_tf0,
transform2=self.train_tf00,
testBooks=self.test_books,
max_batch_length=opt.batch_max_length))
for i in range(len(self.datasets)):
train_sampler = torch.utils.data.distributed.DistributedSampler(
self.datasets[i])
self.data_samplers.append(train_sampler)
self.data_loader_list.append(
DataLoader(self.datasets[i],
num_workers=int(opt.workers),
shuffle=False,
sampler=train_sampler,
batch_size=self.batch_sizes[i],
collate_fn=collate_fn,
pin_memory=True,
drop_last=True))
self.dataloader_iter_list = [iter(i) for i in self.data_loader_list]
self.test_tf = transforms.Compose(
[self.grayimg, self.resizeimg_test,
transforms.ToTensor()])
self.test_dataset = RealImageLMDB(self.train_data[0],
self.test_tf,
testBooks=self.test_books,
isTest=True,
character=opt.character)
self.test_sampler = torch.utils.data.distributed.DistributedSampler(
self.test_dataset)
self.test_loader = DataLoader(self.test_dataset,
num_workers=int(opt.workers),
shuffle=False,
sampler=self.test_sampler,
batch_size=max(2,
int(opt.batch_size / 8)),
collate_fn=collate_fn,
drop_last=True)
def main():
dt_config = Config()
dt_config.display()
train_aug = Compose(
[
GaussNoise(p=1.0),
RandomShadow(p=0.5),
RandomRain(p=0.5, rain_type="drizzle"),
RandomContrast(limit=0.2, p=0.5),
RandomGamma(gamma_limit=(80, 120), p=0.5),
RandomBrightness(limit=0.2, p=0.5),
HueSaturationValue(
hue_shift_limit=5, sat_shift_limit=20, val_shift_limit=10, p=0.5
),
CLAHE(p=0.5, clip_limit=2.0),
Normalize(p=1.0),
]
)
val_aug = Compose([Normalize(p=1.0)])
train_set = KittiStixelDataset(
data_path=dt_config.DATA_PATH,
ground_truth_path=dt_config.GROUND_TRUTH_PATH,
batch_size=parsed_args.batch_size,
phase="train",
transform=train_aug,
customized_transform=utility.HorizontalFlip(p=0.5),
)
val_set = KittiStixelDataset(
data_path=dt_config.DATA_PATH,
ground_truth_path=dt_config.GROUND_TRUTH_PATH,
phase="val",
transform=val_aug,
)
model = build_stixel_net()
loss_func = StixelLoss()
opt = optimizers.Adam(0.0001)
callbacks = [
ModelCheckpoint(
os.path.join(dt_config.SAVED_MODELS_PATH, "model-{epoch:03d}.h5"),
monitor="val_loss",
verbose=1,
save_best_only=True,
mode="auto",
period=1,
),
ReduceLROnPlateau(
monitor="val_loss",
factor=0.1,
patience=7,
verbose=0,
mode="auto",
min_lr=0.000001,
),
EarlyStopping(
monitor="val_loss", min_delta=0, patience=10, verbose=0, mode="auto"
),
]
model.compile(loss=loss_func, optimizer=opt)
model.summary()
history = model.fit_generator(
train_set,
steps_per_epoch=len(train_set),
validation_data=val_set,
validation_steps=len(val_set),
epochs=parsed_args.num_epoch,
callbacks=callbacks,
shuffle=True,
)
history_path = os.path.join(dt_config.SAVED_MODELS_PATH, "history.pkl")
np.save(history_path, history.history)
def ImageAugument():
imgs_save_dir = 'data/albu_imgs/'
if not os.path.exists(imgs_save_dir):
os.makedirs(imgs_save_dir)
xmls_save_dir = 'data/albu_xmls/'
if not os.path.exists(xmls_save_dir):
os.makedirs(xmls_save_dir)
path = "data/img" # 文件夹目录
xml_path = "data/xml"
files = os.listdir(path) # 得到文件夹下的所有文件名称
# 遍历文件夹
prefix = path + '/'
print("begin>>>")
for file in tqdm(files):
image = cv2.imread(prefix + file)
# cv2.imwrite("origin.jpg",image)
xml = xml_path + "/" + file[:-4] + ".xml"
#示例：使用具有随机孔径线性大小的中值滤波器来模糊输入图像
aug = MedianBlur(p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'mb' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "mb" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
#随机大小的内核模糊输入图像
aug = Blur(p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'blur' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "blur" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
#高斯模糊
aug = GaussNoise(p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'gau' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "gau" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
#随机雨
aug = RandomRain(p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'rain' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "rain" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
#随机雾
aug = RandomFog(fog_coef_lower=0.2,
fog_coef_upper=0.5,
alpha_coef=0.1,
p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'fog' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "fog" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
#太阳耀斑RandomSunFlare
aug = RandomSunFlare(p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'sun' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "sun" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
#阴影RandomShadow
aug = RandomShadow(p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'shadow' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "shadow" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
#随机雪RandomSnow
aug = RandomSnow(p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'snow' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "snow" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
#随机CoarseDropout
aug = CoarseDropout(p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'drop' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "drop" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
#随机cutout
aug = Cutout(p=1)
aug_image = aug(image=image)['image']
cv2.imwrite(imgs_save_dir + file[:-4] + 'cut' + '.jpg', aug_image)
new_name = xmls_save_dir + "/" + file[:-4] + "cut" + ".xml" # 为文件赋予新名字
shutil.copyfile(xml, new_name)
print("Done")
