def chapter_augmenters_multiplybrightness():
fn_start = "color/multiplybrightness"
aug = iaa.MultiplyBrightness((0.5, 1.5))
run_and_save_augseq(fn_start + ".jpg",
aug, [ia.quokka(size=(128, 128)) for _ in range(8)],
cols=4,
rows=2)
def __call__(self, *args, **kwargs) -> typing.Tuple[np.ndarray, typing.List[Polygon]]:
if self.is_training:
resize = iaa.Resize(size=dict(longer_side=self.long_sizes,
width='keep-aspect-ratio'))
rotate = iaa.Rotate(rotate=self.angles, fit_output=True)
resize_height = iaa.Resize(size=dict(height=self.height_ratios,
width='keep'))
crop = iaa.CropToFixedSize(width=self.cropped_size[0], height=self.cropped_size[1])
fix_resize = iaa.Resize(size=self.output_size)
# blur = iaa.GaussianBlur()
# blur = iaa.Sometimes(p=self.blur_prob,
# then_list=blur)
brightness = iaa.MultiplyBrightness((0.5, 1.5))
brightness = iaa.Sometimes(self.color_jitter_prob, then_list=brightness)
saturation = iaa.MultiplySaturation((0.5, 1.5))
saturation = iaa.Sometimes(self.color_jitter_prob, then_list=saturation)
contrast = iaa.LinearContrast(0.5)
contrast = iaa.Sometimes(self.color_jitter_prob, then_list=contrast)
hue = iaa.MultiplyHue()
hue = iaa.Sometimes(self.color_jitter_prob, then_list=hue)
augs = [resize,
rotate,
resize_height,
crop,
fix_resize,
brightness,
saturation,
contrast,
hue]
ia = iaa.Sequential(augs)
else:
fix_resize = iaa.Resize(size=self.output_size)
ia = iaa.Sequential([fix_resize])
image = args[0]
polygons = args[1]
polygon_list = []
for i in range(polygons.shape[0]):
polygon_list.append(Polygon(polygons[i].tolist()))
polygons_on_image = PolygonsOnImage(polygon_list, shape=image.shape)
image_aug, polygons_aug = ia(image=image, polygons=polygons_on_image)
return image_aug, polygons_aug.polygons
def ol_aug(image, mask):
# ia.seed(seed)
# Example batch of images.
# The array has shape (32, 64, 64, 3) and dtype uint8.
images = image # B,H,W,C
masks = mask # B,H,W,C
# print('In Aug',images.shape,masks.shape)
combo = np.concatenate((images, masks), axis=3)
# print('COMBO: ',combo.shape)
seq_all = iaa.Sequential([
iaa.Fliplr(0.5), # horizontal flips
# iaa.PadToFixedSize(width=crop_size[0], height=crop_size[1]),
# iaa.CropToFixedSize(width=crop_size[0], height=crop_size[1]),
iaa.Affine(
scale={"x": (0.9, 1.1), "y": (0.9, 1.1)},
# scale images to 90-110% of their size, individually per axis
translate_percent={"x": (-0.1, 0.1), "y": (-0.1, 0.1)},
# translate by -10 to +10 percent (per axis)
rotate=(-5, 5), # rotate by -5 to +5 degrees
shear=(-3, 3), # shear by -3 to +3 degrees
),
# iaa.Cutout(nb_iterations=(1, 5), size=0.2, cval=0, squared=False),
], random_order=False) # apply augmenters in random order
seq_f = iaa.Sequential([
iaa.Sometimes(0.5,
iaa.OneOf([
iaa.GaussianBlur((0.0, 3.0)),
iaa.MotionBlur(k=(3, 20)),
]),
),
iaa.Sometimes(0.5,
iaa.OneOf([
iaa.Multiply((0.8, 1.2), per_channel=0.2),
iaa.MultiplyBrightness((0.5, 1.5)),
iaa.LinearContrast((0.5, 2.0), per_channel=0.2),
iaa.BlendAlpha((0., 1.), iaa.HistogramEqualization()),
iaa.MultiplyHueAndSaturation((0.5, 1.5), per_channel=0.2),
]),
),
], random_order=False)
combo_aug = np.array(seq_all.augment_images(images=combo))
# print('combo_au: ', combo_aug.shape)
images_aug = combo_aug[:, :, :, :3]
masks_aug = combo_aug[:, :, :, 3:]
images_aug = seq_f.augment_images(images=images_aug)
return images_aug, masks_aug
def new_gen_train_trans(image, mask):
image = np.array(image)
mask = np.array(mask)
h, w = mask.shape
th, tw = args.train_size
crop_scales = [1.0, 0.875, 0.75, 0.625, 0.5]
hue_factor = 0.6
brightness_factor = 0.6 # was 0.5
p_flip = 0.5
jpeg_scale = 0, 80 # was 70
p_erase_class = 0.5
crop_scale = np.random.choice(crop_scales)
ch, cw = [int(x * crop_scale) for x in (h, w)]
i = np.random.randint(0, h - ch + 1)
j = np.random.randint(0, w - cw + 1)
image = image[i:i + ch, j:j + cw, :]
mask = mask[i:i + ch, j:j + cw]
brightness = iaa.MultiplyBrightness(
(1 - brightness_factor, 1 + brightness_factor))
hue = iaa.MultiplyHue((1 - hue_factor, 1 + hue_factor))
jpeg = iaa.JpegCompression(compression=jpeg_scale)
img_transforms = iaa.Sequential([brightness, hue, jpeg])
image = img_transforms(image=image)
if np.random.rand() < p_flip:
image = np.flip(image, axis=1)
mask = np.flip(mask, axis=1)
image = Image.fromarray(image)
mask = Image.fromarray(mask)
# Resize, 1 for Image.LANCZOS
image = TF.resize(image, (th, tw), interpolation=1)
# Resize, 0 for Image.NEAREST
mask = TF.resize(mask, (th, tw), interpolation=0)
# From PIL to Tensor
image = TF.to_tensor(image)
# Normalize
image = TF.normalize(image, args.dataset_mean, args.dataset_std)
# Convert ids to train_ids
mask = np.array(mask, np.uint8)
mask = torch.from_numpy(mask) # Numpy array to tensor
return image, mask
def __init__(self):
self.aug = iaa.Sequential([
iaa.Sometimes(0.25, iaa.GaussianBlur(sigma=(0, 3.0))),
# iaa.Fliplr(0.15),
# iaa.Crop(px=(0, 10)),
iaa.Sometimes(0.25, iaa.PerspectiveTransform(0.08)),
iaa.MultiplyBrightness((0.5, 1.5)),
iaa.Affine(rotate=(-10, 10), mode='symmetric'),
iaa.Sometimes(0.25,
iaa.OneOf([iaa.Dropout(p=(0, 0.1)),
iaa.CoarseDropout(0.1, size_percent=0.5)])),
iaa.AddToHueAndSaturation(value=(-10, 10), per_channel=True)
])
def __init__(self, key_source='image', key_target=None):
super(RandomColorJitter, self).__init__(key_source=key_source,
key_target=key_target)
self.sequence = iaa.Sequential([
iaa.Sometimes(
0.8,
iaa.Sequential([
iaa.MultiplyBrightness((0.8, 1.25)),
iaa.MultiplyHueAndSaturation(mul_hue=(0.8, 1.25),
mul_saturation=(0.8, 1.25))
])),
iaa.Sometimes(0.2, iaa.Grayscale())
])
def __init__(self, dataset: Dataset, cfg):
self._dataset = dataset
self.input_shape = cfg.AUGMENT.INPUT_SHAPE
self.zoom_in = cfg.AUGMENT.ZOOM_IN
self.min_scale = cfg.AUGMENT.MIN_SCALE
self.max_scale = cfg.AUGMENT.MAX_SCALE
self.max_try_times = cfg.AUGMENT.MAX_TRY_TIMES
self.flip = cfg.AUGMENT.FLIP
self.aspect_ratio = cfg.AUGMENT.ASPECT_RATIO
self.translate_percent = cfg.AUGMENT.TRANSLATE_PRESENT
self.rotate = cfg.AUGMENT.ROTATE
self.shear = cfg.AUGMENT.SHEAR
self.perspective_transform = cfg.AUGMENT.PERSPECTIVE_TRANSFORM
self.brightness = cfg.AUGMENT.BRIGHTNESS
self.hue = cfg.AUGMENT.HUE
self.saturation = cfg.AUGMENT.SATURATION
self.augment_background = cfg.AUGMENT.BACKGROUND
if self.augment_background:
self.backgrounds = [
os.path.join('../../data/background', item)
for item in os.listdir('../../data/background')
]
self.seq = iaa.Sequential([
iaa.Fliplr(self.flip),
iaa.Affine(scale={
"x": self.aspect_ratio,
"y": self.aspect_ratio
},
translate_percent={
"x": self.translate_percent,
"y": self.translate_percent
},
rotate=self.rotate,
shear=self.shear,
order=[0, 1],
cval=(0, 255)),
iaa.PerspectiveTransform(scale=self.perspective_transform),
iaa.MultiplyBrightness(self.brightness),
iaa.MultiplySaturation(self.saturation),
iaa.MultiplyHue(self.hue)
])
def data_augmentation(path):
ia.seed(2)
seq = iaa.Sequential([
iaa.Sometimes(0.5, iaa.Grayscale(alpha=(0.1, 0.5))),
iaa.Sometimes(0.5, iaa.Multiply((0.5, 1.5), per_channel=0.5)),
iaa.Sometimes(0.5,
iaa.MultiplyHueAndSaturation(mul_saturation=(0.5, 1.5))),
iaa.Sometimes(0.5, iaa.GaussianBlur(sigma=(0, 2.0))),
iaa.Sometimes(0.8, iaa.MultiplyBrightness((0.5, 1.5))),
iaa.AddToBrightness((-30, 30)),
iaa.Sometimes(0.6,
iaa.MultiplyHueAndSaturation(mul_saturation=(0.5, 1.5)))
],
random_order=True)
i = 0
for fname in os.listdir(path):
try:
img = imageio.imread(os.path.join(path, fname), pilmode="RGB")
print(i)
if i % 5 == 0:
img_aug = seq.augment_image(img)
imageio.imwrite(
os.path.join(path, fname.replace(".jpg", "_imgaug.jpg")),
img_aug)
fname_txt = fname.replace('.jpg', '.txt')
print(
os.path.join(path,
fname_txt.replace(".txt", "_imgaug.txt")))
shutil.copyfile(
os.path.join(path, fname_txt),
os.path.join(path,
fname_txt.replace(".txt", "_imgaug.txt")))
except:
print('Error reading img')
i += 1
def __init__(self):
self.aug = iaa.Sequential([
# iaa.HorizontalFlip(p = 0.5),
# iaa.VerticalFlip(p = 0.5),
# iaa.Affine(scale=(0.5, 1.5)),
iaa.Dropout(p=(0, 0.2), per_channel=0.5),
iaa.SomeOf(
(1, 2),
[
# iaa.Cutout(fill_mode="gaussian", fill_per_channel=True),
iaa.SaltAndPepper(0.1),
# iaa.Affine(rotate=(-45, 45), shear=(-16, 16)),
# iaa.imgcorruptlike.GaussianNoise(severity=1),
# iaa.AveragePooling(2),
iaa.AddToHueAndSaturation((-60, 60)),
iaa.MultiplyBrightness(mul=(0.65, 1.35)),
iaa.LinearContrast((0.5, 2.0)),
iaa.GaussianBlur(sigma=(0.5, 2.0)),
# iaa.CoarseDropout((0.01,0.1), size_percent = 0.01)
])
])
def __getitem__(self, index):
co_ords = self.coords[index * BATCH_SIZE:(index + 1) * BATCH_SIZE]
batch_images = np.zeros((len(co_ords), INPUT_HEIGHT, INPUT_WIDTH, 3),
dtype=np.float32)
batch_heatmaps = np.zeros(
(len(co_ords), OUTPUT_HEIGHT, OUTPUT_WIDTH, 2), dtype=np.float32)
for i, row in enumerate(co_ords):
images_path, x, y = row
proc_image = image.load_img(self.image_path + images_path,
target_size=(INPUT_HEIGHT,
INPUT_WIDTH))
proc_image = image.img_to_array(proc_image, dtype='uint8')
heatmap = heatmap_splat(y, x) # y is height and x is width!!
heatmap = np.expand_dims(heatmap, axis=0)
aug_list = iaa.OneOf([
iaa.Dropout([0.05, 0.1]),
iaa.Sharpen((0.0, 1.0)),
iaa.MultiplyHue((0.7, 1.4)),
iaa.MultiplyBrightness((0.7, 1.4)),
])
aug = iaa.Sequential([aug_list, iaa.Fliplr(0.5)],
random_order=True)
proc_image, heatmap = aug.augment(image=proc_image,
heatmaps=heatmap)
proc_image = np.expand_dims(proc_image, axis=0)
proc_image = proc_image / 255. #just for now try without normalising
batch_images[i] = proc_image
batch_heatmaps[i] = heatmap
return batch_images, batch_heatmaps
def init_augmenter(img_mode="color"):
"""Initializes the augmenters used in the training dataset
:param config: the config object that contains all the
"""
ia.seed(10)
if img_mode == 'color':
return iaa.Sequential([
sometimes(iaa.Fliplr()),
iaa.MultiplyBrightness((0.6, 1.4)),
# TODO: try no ChangeColor or Brightness
sometimes(iaa.ChangeColorTemperature((5000, 7000))),
iaa.Crop(percent=(
(0, 0.50),
(0, 0.50),
(0, 0.50),
(0, 0.50)
))
# sometimes(iaa.OneOf([
# iaa.Cutout(nb_iterations=(1, 4), size=0.2,
# squared=False, cval=(0, 255), fill_mode="constant"),
# iaa.Cutout(nb_iterations=(1, 4), size=0.2, squared=False, cval=(
# 0, 255), fill_mode="gaussian", fill_per_channel=True),
# iaa.AdditiveGaussianNoise(scale=(0, 0.1*255))
# ]))
])
else:
return iaa.Sequential([
sometimes(iaa.Fliplr()),
iaa.Crop(percent=(
(0, 0.40),
(0, 0.40),
(0, 0.40),
(0, 0.40)
))
])
# instantiate imgaug augmentation object
sometimes = lambda aug: iaa.Sometimes(0.5, aug)
AUGMENTATIONS = iaa.Sequential([
iaa.Fliplr(0.5),
iaa.Flipud(0.5),
sometimes(iaa.Affine(
scale=(0.8, 1.2),
rotate=(90),
mode=ia.ALL)),
sometimes(iaa.ElasticTransformation(alpha=(0.8, 1.2),\
sigma=(9.0, 11.0))),
sometimes(iaa.AdditiveGaussianNoise(scale=(0, 0.1))),
sometimes(iaa.GaussianBlur((0, 0.1))),
sometimes(iaa.MultiplyBrightness((0.65, 1.35))),
sometimes(iaa.LinearContrast((0.5, 1.5))),
sometimes(iaa.MultiplyHueAndSaturation((-1, 1)))
], random_order=True)
# instantiate datagen objects
train_datagen = ImageDataAugmentor(
# featurewise_center=True,
# featurewise_std_normalization=True,
augment=AUGMENTATIONS,
rescale=1. / 255,
preprocess_input=None)
val_datagen = ImageDataAugmentor(rescale=1. / 255)
# define the ImageNet mean subtraction (in RGB order)
# dataset = NewDataset()
# loader = DataLoader(dataset, batch_size=2)
# for x in loader:
# print(x)
import numpy as np
from imgaug import augmenters as iaa
from torch.utils.data import DataLoader, Dataset
from torchvision import transforms
tfs = transforms.Compose([
iaa.Sequential([
iaa.flip.Fliplr(p=0.5),
iaa.flip.Flipud(p=0.5),
iaa.GaussianBlur(sigma=(0.0, 0.1)),
iaa.MultiplyBrightness(mul=(0.65, 1.35)),
]).augment_image,
transforms.ToTensor()
])
class CustomDataset(Dataset):
def __init__(self, n_images, n_classes, transform=None):
self.images = np.random.randint(0,
255, (n_images, 224, 224, 3),
dtype=np.uint8)
self.targets = np.random.randn(n_images, n_classes)
self.transform = transform
def __getitem__(self, item):
image = self.images[item]
iaa.BlendAlphaElementwise((0.0, 1.0),
foreground=iaa.Add((-15, 15)),
background=iaa.Multiply((0.8, 1.2))),
iaa.ReplaceElementwise(0.05,
iap.Normal(128, 0.4 * 128),
per_channel=0.5),
iaa.Dropout(p=(0, 0.05), per_channel=0.5),
])),
# Brightness + Color + Contrast
iaa.Sometimes(
0.5,
iaa.OneOf([
iaa.Add(iap.Normal(iap.Choice([-30, 30]), 10)),
iaa.Multiply((0.75, 1.25)),
iaa.AddToBrightness((-35, 35)),
iaa.MultiplyBrightness((0.85, 1.15)),
iaa.MultiplyAndAddToBrightness(mul=(0.85, 1.15), add=(-10, 10)),
iaa.BlendAlphaHorizontalLinearGradient(iaa.Add(
iap.Normal(iap.Choice([-40, 40]), 10)),
start_at=(0, 0.2),
end_at=(0.8, 1)),
iaa.BlendAlphaHorizontalLinearGradient(iaa.Add(
iap.Normal(iap.Choice([-40, 40]), 10)),
start_at=(0.8, 1),
end_at=(0, 0.2)),
iaa.BlendAlphaVerticalLinearGradient(iaa.Add(
iap.Normal(iap.Choice([-40, 40]), 10)),
start_at=(0.8, 1),
end_at=(0, 0.2)),
iaa.BlendAlphaVerticalLinearGradient(iaa.Add(
iap.Normal(iap.Choice([-40, 40]), 10)),
def __init__(self):
self.seq = iaa.Sequential(
[
iaa.Fliplr(0.5),
iaa.Sometimes(0.5, iaa.Crop(percent=(0, 0.1))),
iaa.Sometimes(0.5, iaa.Affine(
rotate=(-20, 20), # 旋转±20度
# shear=(-16, 16), # 剪切变换±16度，矩形变平行四边形
# order=[0, 1], # 使用最近邻插值 或 双线性插值
cval=0, # 填充值
mode=ia.ALL # 定义填充图像外区域的方法
)),
# 使用0~3个方法进行图像增强
iaa.SomeOf((0, 3),
[
iaa.Sometimes(0.8, iaa.OneOf([
iaa.GaussianBlur((0, 2.0)), # 高斯模糊
iaa.AverageBlur(k=(1, 5)), # 平均模糊，磨砂
])),
# 要么运动，要么美颜
iaa.Sometimes(0.8, iaa.OneOf([
iaa.MotionBlur(k=(3, 11)), # 运动模糊
iaa.BilateralBlur(d=(1, 5),
sigma_color=(10, 250),
sigma_space=(10, 250)), # 双边滤波，美颜
])),
# 模仿雪花
iaa.Sometimes(0.8, iaa.OneOf([
iaa.SaltAndPepper(p=(0., 0.03)),
iaa.AdditiveGaussianNoise(loc=0, scale=(0., 0.05 * 255), per_channel=False)
])),
# 对比度
iaa.Sometimes(0.8, iaa.LinearContrast((0.6, 1.4), per_channel=0.5)),
# 锐化
iaa.Sometimes(0.8, iaa.Sharpen(alpha=(0, 1.0), lightness=(0.75, 1.5))),
# 整体亮度
iaa.Sometimes(0.8, iaa.OneOf([
# 加性调整
iaa.AddToBrightness((-30, 30)),
# 线性调整
iaa.MultiplyBrightness((0.5, 1.5)),
# 加性 & 线性
iaa.MultiplyAndAddToBrightness(mul=(0.5, 1.5), add=(-30, 30)),
])),
# 饱和度
iaa.Sometimes(0.8, iaa.OneOf([
iaa.AddToSaturation((-75, 75)),
iaa.MultiplySaturation((0., 3.)),
])),
# 色相
iaa.Sometimes(0.8, iaa.OneOf([
iaa.AddToHue((-255, 255)),
iaa.MultiplyHue((-3.0, 3.0)),
])),
# 云雾
# iaa.Sometimes(0.3, iaa.Clouds()),
# 卡通化
# iaa.Sometimes(0.01, iaa.Cartoon()),
],
random_order=True
)
],
random_order=True
)
save_model_dir = '/tmp2/wide_angel'
train_type = 'wide_angle'
data_version = 'v4'
csv_train = Path(__file__).parent.parent.absolute().joinpath(
'datafiles', data_version, 'train.csv')
csv_valid = Path(__file__).parent.parent.absolute().joinpath(
'datafiles', data_version, 'valid.csv')
csv_test = Path(__file__).parent.parent.absolute().joinpath(
'datafiles', data_version, 'test.csv')
iaa = iaa.Sequential([
# iaa.CropAndPad(percent=(-0.04, 0.04)),
iaa.Fliplr(0.5),
iaa.Flipud(0.25),
iaa.GaussianBlur(sigma=(0.0, 0.3)),
iaa.MultiplyBrightness(mul=(0.7, 1.3)),
iaa.contrast.LinearContrast((0.7, 1.3)),
iaa.Sometimes(0.9, iaa.Add((-8, 8))),
iaa.Sometimes(
0.9,
iaa.Affine(
scale=(0.98, 1.02),
translate_percent={
"x": (-0.06, 0.06),
"y": (-0.06, 0.06)
},
rotate=(-15, 15),
)),
])
batch_size_train, batch_size_valid = 32, 64
import cv2
import os
import uuid
filename_csv = 'fovea.csv'
image_shape = (299, 299)
dir_tmp = '/tmp2/dataset_test/'
iaa = iaa.Sequential([
# iaa.CropAndPad(percent=(-0.04, 0.04)),
iaa.Fliplr(0.5), # horizontally flip 50% of the images
iaa.Flipud(0.2), # horizontally flip 50% of the images
iaa.GaussianBlur(sigma=(0.0, 0.5)),
iaa.MultiplyBrightness(mul=(0.8, 1.2)),
iaa.contrast.LinearContrast((0.8, 1.2)),
iaa.Sometimes(0.9, iaa.Add((-8, 8))),
iaa.Sometimes(0.9, iaa.Affine(
scale=(0.98, 1.02),
translate_percent={"x": (-0.06, 0.06), "y": (-0.06, 0.06)},
rotate=(-15, 15),
)),
])
iaa = None
batch_size = 32
dataset= Dataset_CSV(csv_file=filename_csv, imgaug_iaa=iaa, image_shape=image_shape)
loader = DataLoader(dataset, batch_size=batch_size,
import numpy as np
from imgaug import augmenters as iaa
from torch.utils.data import DataLoader, Dataset
from torchvision import transforms
from skimage import io
import os
tfs = transforms.Compose([
iaa.Sequential([
iaa.Sometimes(0.5, iaa.Fliplr(1.0)),
iaa.Sometimes(0.5, iaa.MultiplyBrightness((0.3, 1.3))),
iaa.Sometimes(0.2, iaa.ChangeColorTemperature((4300, 6000))),
#iaa.Sometimes(0.9, iaa.Affine(rotate=(-180, 180), shear=(-6, 6))),
]).augment_image,
transforms.ToTensor()
])
class CustomDataset(Dataset):
def __init__(self, n_images, n_classes=15, transform=None):
self.images = []
self.transform = transform
test_path = "/content/gdrive/My Drive/Arirang/data/test/images"
file_list = os.listdir(test_path)
file_list_png = [file for file in file_list if file.endswith(".png")]
for idx, filename in enumerate(file_list_png):
self.images.append( os.path.join(test_path, filename))
# save to local
# read from local
# f = open("dict.txt", 'r')
# dict_ = eval(f.read())
# f.close()
# print("read from local : ", dict_)
def getImageVar(img):
img=cv2.cvtColor(img,cv2.COLOR_RGB2GRAY)
imagevar=cv2.Laplacian(img,cv2.CV_64F).var()
return imagevar
aug_brightness = iaa.MultiplyBrightness((0.7, 1.1))
aug_gaussian =iaa.GaussianBlur((0, 2.0))
kernel_sharpen_1 = np.array([
[-1, -1, -1],
[-1, 9, -1],
[-1, -1, -1]])
path='/home/ubuntu/hks/ocr/idcard_generator_project/idcard_pix2pix/data_train_with_aug/'
dirs=os.listdir(path)
d_dict={}
for d in dirs:
d_dict[d+'_0']=0
d_dict[d+'_1']=0
l=[]
for i in range(1,20):
for index,d in enumerate(dirs):
# os.mkdir('/home/ubuntu/hks/ocr/idcard_generator_project/idcard_pix2pix/data_val_with_aug/'+d)
transformed_image = transform(image=image)['image']
elif augmentation == 'brightness':
transform = iaa.imgcorruptlike.Brightness(severity=2)
transformed_image = transform(image=image)
elif augmentation == 'addto_hue_and_saturation':
transform = iaa.AddToHueAndSaturation((-50, 50), per_channel=True)
transformed_image = transform(image=image)
elif augmentation == 'hue_saturation':
transform = HueSaturationValue(always_apply=True)
transformed_image = transform(image=image)['image']
elif augmentation == 'multiply_brightness':
transform = iaa.MultiplyBrightness((0.1, 1.9))
transformed_image = transform(image=image)
elif augmentation == 'addto_brightness':
transform = iaa.AddToBrightness((-50, 50))
transformed_image = transform(image=image)
elif augmentation == 'multiply_and_addtobrightness':
transform = iaa.MultiplyAndAddToBrightness(mul=(0.5, 1.5),
add=(-30, 30))
transformed_image = transform(image=image)
elif augmentation == 'to_gray':
transform = ToGray(always_apply=True)
transformed_image = transform(image=image)['image']
image = tf.image.random_crop(image,
[tf.shape(image)[0], *INPUT_SHAPE[:2], 3])
return image, target
# resize image to 224x224
def resize_image(image, target):
image = tf.image.resize(image, INPUT_SHAPE[:2])
return image, target
# augmentation options
AUG = iaa.Sequential([
iaa.SomeOf((0, 1), [
iaa.AddToBrightness((-30, 30)),
iaa.MultiplyBrightness((0.5, 1.5)),
iaa.MultiplySaturation((0.5, 1.5)),
iaa.AddToSaturation((-50, 50))
]),
iaa.OneOf([
iaa.ScaleX((1.0, 1.5)),
iaa.ScaleY((1.0, 1.5)),
iaa.Affine(scale={
"x": (1.0, 1.2),
"y": (1.0, 1.2)
}),
iaa.Affine(rotate=(-20, 20)),
iaa.PiecewiseAffine(scale=(0.01, 0.05)),
iaa.Affine(shear=(-16, 16))
]),
iaa.Fliplr(0.5),
def main():
try:
config_dirs_file = sys.argv[1] # directories file
config_file = sys.argv[2] # main params file
except:
print("Config file names not specified, setting them to default namess")
config_dirs_file = "config_dirs.json"
config_file = "config760.json"
print(f'USING CONFIG FILES: config dirs:{config_dirs_file} main config:{config_file}')
#print(type(feature_directory))
C = cs760.loadas_json('config760.json')
print("Running with parameters:", C)
Cdirs = cs760.loadas_json(config_dirs_file)
print("Directories:", Cdirs)
C['dirs'] = Cdirs
video_directory = C['dirs']['indir']
feature_directory = C['dirs']['outdir']
print(f'Creating feature file Dir: {feature_directory}')
os.makedirs(feature_directory, exist_ok=True) #if dir already exists will continue and WILL NOT delete existing files in that directory
sometimes = lambda aug: iaa.Sometimes(C["augmentation_chance"][0], aug)
sequential_list = [iaa.Sequential([sometimes(iaa.Fliplr(1.0))]), # horizontal flip
iaa.Sequential([sometimes(iaa.Rotate(-5, 5))]), # rotate 5 degrees +/-
iaa.Sequential([sometimes(iaa.CenterCropToAspectRatio(1.15))]),
iaa.Sequential([sometimes(iaa.MultiplyBrightness((2.0, 2.0)))]), # increase brightness
iaa.Sequential([sometimes(iaa.MultiplyHue((0.5, 1.5)))]), # change hue random
iaa.Sequential([sometimes(iaa.RemoveSaturation(1.0))]), # effectively greyscale
iaa.Sequential([sometimes(iaa.pillike.FilterContour())]), # edge detection
iaa.Sequential([sometimes(iaa.AdditiveLaplaceNoise(scale=0.05*255, per_channel=True))]), # add colourful noise
iaa.Sequential([sometimes(iaa.Invert(1))]) # invert colours
]
print("Reading videos from " + video_directory)
print("Outputting features to " + feature_directory)
print("Loading pretrained CNN...")
model = hub.KerasLayer(C["module_url"]) # can be used like any other kera layer including in other layers...
print("Pretrained CNN Loaded OK")
vids = cs760.list_files_pattern(video_directory, C["vid_type"])
print(f'Processing {len(vids)} videos...')
for i, vid in enumerate(vids):
print(f'{i} Processing: {vid}')
vid_np = cs760.get_vid_frames(vid,
video_directory,
writejpgs=False,
writenpy=False,
returnnp=True)
(framecount, frameheight, framewidth, channels) = vid_np.shape
res_key = str(frameheight) + "-" + str(framewidth)
#print(vid, vid_np.shape)
outfile = os.path.splitext(vid)[0]
print(f"Vid frames, h, w, c = {(framecount, frameheight, framewidth, channels)}")
if C["crop_by_res"].get(res_key) is not None:
vid_np_top = cs760.crop_image(vid_np, C["crop_by_res"][res_key])
print(f"Cropped by resolution to {C['crop_by_res'][res_key]}")
else:
vid_np_top = cs760.crop_image(vid_np, C["crop_top"])
print(f"Cropped by default to {C['crop_top']}")
outfile_top = outfile + "__TOP.pkl"
for n in range((len(sequential_list) + 1)):
if n != 0:
vid_aug = sequential_list[n - 1](images=vid_np_top) # augments frames
if type(vid_aug) is list:
vid_aug = np.asarray(vid_aug)
batch = cs760.resize_batch(vid_aug, width=C["expect_img_size"], height=C["expect_img_size"], pad_type='L',
inter=cv2.INTER_CUBIC, BGRtoRGB=False,
simplenormalize=True,
imagenetmeansubtract=False)
temp_outfile = outfile_top[:-4] + C["augmentation_type"][n - 1] + ".pkl"
features = extract(C, model, batch)
cs760.saveas_pickle(features, os.path.join(feature_directory, temp_outfile))
else:
batch = cs760.resize_batch(vid_np_top, width=C["expect_img_size"], height=C["expect_img_size"], pad_type='L',
inter=cv2.INTER_CUBIC, BGRtoRGB=False,
simplenormalize=True,
imagenetmeansubtract=False)
features = extract(C, model, batch)
cs760.saveas_pickle(features, os.path.join(feature_directory, outfile_top))
print(f'Features output shape: {features.shape}')
if C["crop_type"] == 'B': # only for boston vids
vid_np_bot = cs760.crop_image(vid_np, C["crop_bottom"])
outfile_bot = outfile + "__BOT.pkl"
batch = cs760.resize_batch(vid_np_bot, width=C["expect_img_size"], height=C["expect_img_size"], pad_type='L',
inter=cv2.INTER_CUBIC, BGRtoRGB=False,
simplenormalize=True,
imagenetmeansubtract=False)
features = extract(C, model, batch)
cs760.saveas_pickle(features, os.path.join(feature_directory, outfile_bot))
print('Finished outputting features!!')
def augumentation(train_set):
img_final_height = int(375 * 0.7)
img_final_width = int(500 * 0.7)
#The transform function for train data
# transform_train = transforms.Compose([
# transforms.Resize((int(img_final_height*1.1),int(img_final_width*1.1))),
# transforms.RandomCrop((img_final_height,img_final_width), padding=4),
# # transforms.Resize(224),
# transforms.ToTensor(),
# #transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
# transforms.Normalize(mean=[0.485, 0.456, 0.406],
# std=[0.229, 0.224, 0.225])
# ])
# transform_train = transforms.Compose([
# transforms.Resize((256,128), interpolation=transforms.InterpolationMode.BICUBIC),
# transforms.RandomHorizontalFlip(0.5),
# transforms.Pad(10),
# transforms.RandomCrop((256,128)),
# transforms.ToTensor(),
# transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225]),
# RandomErasing(probability=0.5, mean=([0.485, 0.456, 0.406]))
# ])
transform_train = transforms.Compose([
transforms.Resize(
(int(img_final_height * 1.1), int(img_final_width * 1.1))),
transforms.RandomCrop((img_final_height, img_final_width), padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]),
RandomErasing(probability=0.5, mean=([0.485, 0.456, 0.406]))
])
# transform_train= transforms.Compose([
# iaa.Sequential([
# iaa.flip.Fliplr(p=0.5),
# iaa.flip.Flipud(p=0.5),
# iaa.GaussianBlur(sigma=(0.0, 0.1)),
# iaa.MultiplyBrightness(mul=(0.65, 1.35)),
# ]).augment_image,
# transforms.ToTensor()
# ])
seq = iaa.Sequential([
iaa.flip.Flipud(p=0.5),
iaa.MultiplyBrightness(mul=(0.65, 1.35)),
#iaa.GammaContrast(1.5),
iaa.AdditiveGaussianNoise(loc=0,
scale=(0.0, 0.05 * 255),
per_channel=0.5),
iaa.Fliplr(p=0.5), # 水平翻轉影象
iaa.GaussianBlur(sigma=(0, 3.0)), # 使用0到3.0的sigma模糊影象
# Small gaussian blur with random sigma between 0 and 0.5.
# But we only blur about 50% of all images.
iaa.Sometimes(0.5, iaa.GaussianBlur(sigma=(0, 0.5))),
# Add gaussian noise.
# For 50% of all images, we sample the noise once per pixel.
# For the other 50% of all images, we sample the noise per pixel AND
# channel. This can change the color (not only brightness) of the
# pixels.
iaa.AdditiveGaussianNoise(loc=0,
scale=(0.0, 0.05 * 255),
per_channel=0.5),
# Make some images brighter and some darker.
# In 20% of all cases, we sample the multiplier once per channel,
# which can end up changing the color of the images.
iaa.Multiply((0.8, 1.2), per_channel=0.8)
# Apply affine transformations to each image.
# Scale/zoom them, translate/move them, rotate them and shear them.
])
#The transform function for test data
# trainset.setImgaug(seq)
train_set.setTransform(transform_train)
return train_set
def gen_faker_card_run():
aug_brightness = iaa.MultiplyBrightness((0.5, 1.))
aug_gaussian =iaa.GaussianBlur((0, 2.0))
# blur images with a sigma between 0 and 3.0
csv_file = open(ori_csv_file, 'r', encoding='UTF-8')
csv_reader_lines = list(csv.reader(csv_file))
csv_reader_lines_train,csv_reader_lines_val=train_test_split(csv_reader_lines,test_size=0.000001, random_state=0)# 逐行读取csv文件
date = [] # 创建列表准备接收csv各行数据
cnt = 0 # 记录csv文件行数
path='/home/ubuntu/hks/ocr/idcard_generator_project/idcard_generator/template/'
files = os.listdir(os.path.join(path, 'fuzhiwuxiao_mask'))
for one_line in csv_reader_lines_train:
date.append(one_line)
image_name=date[cnt][0]
result_front = []
result_back = []
result_front.append(date[cnt][1]) # 姓名
result_front.append(date[cnt][3]) # 性别
result_front.append(date[cnt][2]) # 名族
result_front.append(date[cnt][4]) # 年
result_front.append(date[cnt][5]) # 月
result_front.append(date[cnt][6]) # 日
result_front.append(date[cnt][7]) # 地址
result_front.append(date[cnt][8]) # 身份号
result_back.append(date[cnt][9]) # 签发机关
result_back.append(date[cnt][10]) # 有效日期
image1 = cv2.imread(front_img) # 读取正面模板
image2 = cv2.imread(back_img) # 读取背面模板
#img_new_white1 = img_to_white(image1)
img_new_white1 = image1
# cv2.imshow('hjs',img_new_white1)
# cv2.waitKey(0)# 生成画布
img_res_f = gen_card_front(img_new_white1, result_front)
img_res_f = cv2.cvtColor(img_res_f,cv2.COLOR_BGR2GRAY)
# 写入文字
#cv2.imwrite(result_card_path + '/{}_1.jpg'.format(image_name), img_res_f)
#img_new_white2 = img_to_white(image2)
img_new_white2 = image2
img_res_b = gen_card_back(img_new_white2, result_back)
img_res_b = cv2.cvtColor(img_res_b, cv2.COLOR_BGR2GRAY)
#cv2.imwrite(result_card_path + '/{}_0.jpg'.format(image_name), img_res_b)
cnt = cnt + 1
print(cnt)
for i in range(4):
l = len(files)
index = np.random.randint(0, l)
image_gen_copy = img_res_f.copy()
mask = cv2.imread(os.path.join(path + 'fuzhiwuxiao_mask', files[index]), 0)
mask[mask > 150] = 255
mask[mask <= 150] = 0
image = cv2.imread(os.path.join(path + 'fuzhiwuxiao_template', files[index]), 0)
image = cv2.blur(image, ksize=(5, 5))
image = image + 20
template = cv2.bitwise_and(image, image, mask=mask)
h_image_gen, w_image_gen= img_res_f.shape
point_x, point_y = h_image_gen, w_image_gen
h, w = template.shape
while point_x + h >= h_image_gen or point_y + w >= w_image_gen:
point_x, point_y = np.random.randint(0, h_image_gen), np.random.randint(0, w_image_gen)
rect = image_gen_copy[point_x:(h + point_x), point_y:(w + point_y)]
rect1 = cv2.bitwise_and(rect, rect, mask=mask)
mask = cv2.bitwise_not(mask)
rect2 = cv2.bitwise_and(rect, rect, mask=mask)
image_with_logo = cv2.addWeighted(rect1, 0.3, template, 0.3, 0)
add_logo = image_with_logo + rect2
image_gen_copy_logo = image_gen_copy.copy()
image_gen_copy_logo[point_x:(h + point_x), point_y:(w + point_y)] = add_logo
image_gen_copy_logo=np.stack([image_gen_copy_logo,image_gen_copy_logo,image_gen_copy_logo],axis=2)
aug_brightness_deterministic= aug_brightness.to_deterministic()
aug_gaussian_deterministic=aug_gaussian.to_deterministic()
image_gen_copy_logo=aug_brightness_deterministic.augment_images(images=[image_gen_copy_logo])[0]
image_gen_copy_logo=aug_gaussian_deterministic.augment_images(images=[image_gen_copy_logo])[0]
image_gen_copy = np.stack([image_gen_copy, image_gen_copy, image_gen_copy], axis=2)
image_gen_copy = aug_brightness_deterministic.augment_images(images=[image_gen_copy])[0]
image_gen_copy = aug_gaussian_deterministic.augment_images(images=[image_gen_copy])[0]
#image_gen_copy=seq_nologo(image=np.stack([image_gen_copy,image_gen_copy,image_gen_copy],axis=2))
train_data = np.hstack((image_gen_copy_logo,image_gen_copy))
# cv2.imshow('image', train_data)
# cv2.waitKey(300)
#image_gen_copy[point_x:(h + point_x), point_y:(w + point_y)] = add_logo[:,:]
if os.path.exists('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/train/' +
image_name)==False:
os.mkdir('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/train/' +
image_name)
cv2.imwrite('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/train/' +image_name+'/'+
image_name +'_'+'1'+ '-' + str(i) + '.jpg', train_data)
for i in range(4):
l = len(files)
index = np.random.randint(0, l)
image_gen_copy = img_res_b.copy()
mask = cv2.imread(os.path.join(path + 'fuzhiwuxiao_mask', files[index]), 0)
mask[mask > 150] = 255
mask[mask <= 150] = 0
image = cv2.imread(os.path.join(path + 'fuzhiwuxiao_template', files[index]), 0)
image = cv2.blur(image, ksize=(5, 5))
image = image + 50
template = cv2.bitwise_and(image, image, mask=mask)
h_image_gen, w_image_gen = img_res_b.shape
point_x, point_y = h_image_gen, w_image_gen
h, w = template.shape
while point_x + h >= h_image_gen or point_y + w >= w_image_gen:
l_point = len(point_select)
l_index = np.random.randint(0, l_point)
point_x, point_y = point_select[l_index]
rect = image_gen_copy[point_x:(h + point_x), point_y:(w + point_y)]
rect1 = cv2.bitwise_and(rect, rect, mask=mask)
mask = cv2.bitwise_not(mask)
rect2 = cv2.bitwise_and(rect, rect, mask=mask)
image_with_logo = cv2.addWeighted(rect1, 0.3, template, 0.3, 0)
add_logo = image_with_logo + rect2
image_gen_copy_logo = image_gen_copy.copy()
image_gen_copy_logo[point_x:(h + point_x), point_y:(w + point_y)] = add_logo
image_gen_copy_logo=np.stack([image_gen_copy_logo,image_gen_copy_logo,image_gen_copy_logo],axis=2)
aug_brightness_deterministic= aug_brightness.to_deterministic()
aug_gaussian_deterministic=aug_gaussian.to_deterministic()
image_gen_copy_logo=aug_brightness_deterministic.augment_images(images=[image_gen_copy_logo])[0]
image_gen_copy_logo=aug_gaussian_deterministic.augment_images(images=[image_gen_copy_logo])[0]
image_gen_copy = np.stack([image_gen_copy, image_gen_copy, image_gen_copy], axis=2)
image_gen_copy = aug_brightness_deterministic.augment_images(images=[image_gen_copy])[0]
image_gen_copy = aug_gaussian_deterministic.augment_images(images=[image_gen_copy])[0]
train_data = np.hstack((image_gen_copy_logo,image_gen_copy))
# cv2.imshow('template', template)
# cv2.imshow('logo',image_with_logo)
# cv2.imshow('image_gen',image_gen_copy)
# #cv2.imshow('rect',rect2)
# # cv2.imshow('image', train_data)
# cv2.waitKey(300000)
if os.path.exists('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/train/' +
image_name) == False:
os.mkdir('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/train/' +
image_name)
cv2.imwrite('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/train/'+image_name+'/' +
image_name+'_'+'0'+ '-' + str(i) + '.jpg', train_data)
del image_gen_copy_logo
for one_line in csv_reader_lines_val:
date.append(one_line)
image_name=date[cnt][0]
result_front = []
result_back = []
result_front.append(date[cnt][1]) # 姓名
result_front.append(date[cnt][3]) # 性别
result_front.append(date[cnt][2]) # 名族
result_front.append(date[cnt][4]) # 年
result_front.append(date[cnt][5]) # 月
result_front.append(date[cnt][6]) # 日
result_front.append(date[cnt][7]) # 地址
result_front.append(date[cnt][8]) # 身份号
result_back.append(date[cnt][9]) # 签发机关
result_back.append(date[cnt][10]) # 有效日期
image1 = cv2.imread(front_img) # 读取正面模板
image2 = cv2.imread(back_img) # 读取背面模板
#img_new_white1 = img_to_white(image1)
img_new_white1 = image1
# cv2.imshow('hjs',img_new_white1)
# cv2.waitKey(0)# 生成画布
img_res_f = gen_card_front(img_new_white1, result_front)
img_res_f = cv2.cvtColor(img_res_f,cv2.COLOR_BGR2GRAY)
# 写入文字
#cv2.imwrite(result_card_path + '/{}_1.jpg'.format(image_name), img_res_f)
#img_new_white2 = img_to_white(image2)
img_new_white2 = image2
img_res_b = gen_card_back(img_new_white2, result_back)
img_res_b = cv2.cvtColor(img_res_b, cv2.COLOR_BGR2GRAY)
#cv2.imwrite(result_card_path + '/{}_0.jpg'.format(image_name), img_res_b)
cnt = cnt + 1
print(cnt)
for i in range(4):
l = len(files)
index = np.random.randint(0, l)
image_gen_copy = img_res_f.copy()
mask = cv2.imread(os.path.join(path + 'fuzhiwuxiao_mask', files[index]), 0)
mask[mask > 150] = 255
mask[mask <= 150] = 0
image = cv2.imread(os.path.join(path + 'fuzhiwuxiao_template', files[index]), 0)
template = cv2.bitwise_and(image, image, mask=mask)
h_image_gen, w_image_gen= img_res_f.shape
point_x, point_y = h_image_gen, w_image_gen
h, w = template.shape
while point_x + h >= h_image_gen or point_y + w >= w_image_gen:
point_x, point_y = np.random.randint(0, h_image_gen), np.random.randint(0, w_image_gen)
rect = image_gen_copy[point_x:(h + point_x), point_y:(w + point_y)]
rect1 = cv2.bitwise_and(rect, rect, mask=mask)
mask = cv2.bitwise_not(mask)
rect2 = cv2.bitwise_and(rect, rect, mask=mask)
image_with_logo = cv2.addWeighted(rect1, 0.3, template, 0.3, 0)
add_logo = image_with_logo + rect2
image_gen_copy_logo = image_gen_copy.copy()
image_gen_copy_logo[point_x:(h + point_x), point_y:(w + point_y)] = add_logo
image_gen_copy_logo = np.stack([image_gen_copy_logo, image_gen_copy_logo, image_gen_copy_logo], axis=2)
aug_brightness_deterministic = aug_brightness.to_deterministic()
aug_gaussian_deterministic = aug_gaussian.to_deterministic()
image_gen_copy_logo = aug_brightness_deterministic.augment_images(images=[image_gen_copy_logo])[0]
image_gen_copy_logo = aug_gaussian_deterministic.augment_images(images=[image_gen_copy_logo])[0]
image_gen_copy = np.stack([image_gen_copy, image_gen_copy, image_gen_copy], axis=2)
image_gen_copy = aug_brightness_deterministic.augment_images(images=[image_gen_copy])[0]
#image_gen_copy = aug_gaussian_deterministic.augment_images(images=[image_gen_copy])[0]
#image_gen_copy=seq_nologo(image=np.stack([image_gen_copy,image_gen_copy,image_gen_copy],axis=2))
train_data = np.hstack((image_gen_copy_logo,image_gen_copy))
#image_gen_copy[point_x:(h + point_x), point_y:(w + point_y)] = add_logo[:,:]
if os.path.exists('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/val/' +
image_name) == False:
os.mkdir('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/val/' +
image_name)
cv2.imwrite('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/val/' +image_name+'/'+
image_name +'_'+'0'+ '-' + str(i) + '.jpg', train_data)
for i in range(4):
l = len(files)
index = np.random.randint(0, l)
image_gen_copy = img_res_b.copy()
mask = cv2.imread(os.path.join(path + 'fuzhiwuxiao_mask', files[index]), 0)
mask[mask > 150] = 255
mask[mask <= 150] = 0
image = cv2.imread(os.path.join(path + 'fuzhiwuxiao_template', files[index]), 0)
template = cv2.bitwise_and(image, image, mask=mask)
h_image_gen, w_image_gen = img_res_b.shape
point_x, point_y = h_image_gen, w_image_gen
h, w = template.shape
while point_x + h >= h_image_gen or point_y + w >= w_image_gen:
l_point = len(point_select)
l_index = np.random.randint(0, l_point)
point_x, point_y = point_select[l_index]
rect = image_gen_copy[point_x:(h + point_x), point_y:(w + point_y)]
rect1 = cv2.bitwise_and(rect, rect, mask=mask)
mask = cv2.bitwise_not(mask)
rect2 = cv2.bitwise_and(rect, rect, mask=mask)
image_with_logo = cv2.addWeighted(rect1, 0.3, template, 0.3, 0)
add_logo = image_with_logo + rect2
image_gen_copy_logo = image_gen_copy.copy()
image_gen_copy_logo[point_x:(h + point_x), point_y:(w + point_y)] = add_logo
image_gen_copy_logo = np.stack([image_gen_copy_logo, image_gen_copy_logo, image_gen_copy_logo], axis=2)
aug_brightness_deterministic = aug_brightness.to_deterministic()
aug_gaussian_deterministic = aug_gaussian.to_deterministic()
image_gen_copy_logo = aug_brightness_deterministic.augment_images(images=[image_gen_copy_logo])[0]
image_gen_copy_logo = aug_gaussian_deterministic.augment_images(images=[image_gen_copy_logo])[0]
image_gen_copy = np.stack([image_gen_copy, image_gen_copy, image_gen_copy], axis=2)
image_gen_copy = aug_brightness_deterministic.augment_images(images=[image_gen_copy])[0]
#image_gen_copy = aug_gaussian_deterministic.augment_images(images=[image_gen_copy])[0]
train_data = np.hstack((image_gen_copy_logo,image_gen_copy))
# cv2.imshow('template', template)
# cv2.imshow('logo',image_with_logo)
# cv2.imshow('image_gen',image_gen_copy)
# #cv2.imshow('rect',rect2)
# # cv2.imshow('image', train_data)
# cv2.waitKey(300000)
if os.path.exists('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/val/' +
image_name) == False:
os.mkdir('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/val/' +
image_name)
cv2.imwrite('/home/ubuntu/hks/ocr/idcard_generator_project/remove_logo_and_aug_image/val/' +image_name+'/'+
image_name+'_'+'1'+ '-' + str(i) + '.jpg', train_data)
del image_gen_copy_logo
save_dir_img = 'vitamin_aug3'
save_dir_seg = 'vitamin_aug3_seg'
save_dir_out = 'vitamin_aug3_out'
os.makedirs(save_dir_img, exist_ok=True)
os.makedirs(save_dir_seg, exist_ok=True)
os.makedirs(save_dir_out, exist_ok=True)
file_list_img = glob('%s/*.png' % load_dir_img)
file_list_seg = glob('%s/*.png' % load_dir_img)
aug1 = iaa.PerspectiveTransform(scale=(0, 0.15))
aug2 = iaa.Affine(scale={"x": (0.5, 1), "y": (0.5, 1)})
aug3 = iaa.Affine(translate_percent={"x": (-0.25, 0.25), "y": (-0.25, 0.25)})
aug4 = iaa.MultiplyBrightness((0.8, 1.2))
#aug4 = iaa.Affine(rotate=(-90, 90))
seq = iaa.Sequential([aug1, aug2, aug3])
aug_num = 20
img_ind = 1
for file_path in file_list_img:
print('%d/%d' % (img_ind, len(file_list_img)))
file_name = os.path.basename(file_path)
img = cv2.imread('%s/%s' % (load_dir_img, file_name))
seg = cv2.imread('%s/%s_0.png' % (load_dir_seg, file_name[:-4]))
out = cv2.Canny(img, 30, 50)
cv2.imwrite('%s/%s_aug00.png' % (save_dir_img, file_name[:-4]), img)
cv2.imwrite('%s/%s_aug00.png' % (save_dir_seg, file_name[:-4]), seg)
cv2.imwrite('%s/%s_aug00.png' % (save_dir_out, file_name[:-4]), out)
def create_augmenters(height, width, height_augmentable, width_augmentable, only_augmenters):
def lambda_func_images(images, random_state, parents, hooks):
return images
def lambda_func_heatmaps(heatmaps, random_state, parents, hooks):
return heatmaps
def lambda_func_keypoints(keypoints, random_state, parents, hooks):
return keypoints
def assertlambda_func_images(images, random_state, parents, hooks):
return True
def assertlambda_func_heatmaps(heatmaps, random_state, parents, hooks):
return True
def assertlambda_func_keypoints(keypoints, random_state, parents, hooks):
return True
augmenters_meta = [
iaa.Sequential([iaa.Noop(), iaa.Noop()], random_order=False, name="Sequential_2xNoop"),
iaa.Sequential([iaa.Noop(), iaa.Noop()], random_order=True, name="Sequential_2xNoop_random_order"),
iaa.SomeOf((1, 3), [iaa.Noop(), iaa.Noop(), iaa.Noop()], random_order=False, name="SomeOf_3xNoop"),
iaa.SomeOf((1, 3), [iaa.Noop(), iaa.Noop(), iaa.Noop()], random_order=True, name="SomeOf_3xNoop_random_order"),
iaa.OneOf([iaa.Noop(), iaa.Noop(), iaa.Noop()], name="OneOf_3xNoop"),
iaa.Sometimes(0.5, iaa.Noop(), name="Sometimes_Noop"),
iaa.WithChannels([1, 2], iaa.Noop(), name="WithChannels_1_and_2_Noop"),
iaa.Identity(name="Identity"),
iaa.Noop(name="Noop"),
iaa.Lambda(func_images=lambda_func_images, func_heatmaps=lambda_func_heatmaps, func_keypoints=lambda_func_keypoints,
name="Lambda"),
iaa.AssertLambda(func_images=assertlambda_func_images, func_heatmaps=assertlambda_func_heatmaps,
func_keypoints=assertlambda_func_keypoints, name="AssertLambda"),
iaa.AssertShape((None, height_augmentable, width_augmentable, None), name="AssertShape"),
iaa.ChannelShuffle(0.5, name="ChannelShuffle")
]
augmenters_arithmetic = [
iaa.Add((-10, 10), name="Add"),
iaa.AddElementwise((-10, 10), name="AddElementwise"),
#iaa.AddElementwise((-500, 500), name="AddElementwise"),
iaa.AdditiveGaussianNoise(scale=(5, 10), name="AdditiveGaussianNoise"),
iaa.AdditiveLaplaceNoise(scale=(5, 10), name="AdditiveLaplaceNoise"),
iaa.AdditivePoissonNoise(lam=(1, 5), name="AdditivePoissonNoise"),
iaa.Multiply((0.5, 1.5), name="Multiply"),
iaa.MultiplyElementwise((0.5, 1.5), name="MultiplyElementwise"),
iaa.Cutout(nb_iterations=1, name="Cutout-fill_constant"),
iaa.Dropout((0.01, 0.05), name="Dropout"),
iaa.CoarseDropout((0.01, 0.05), size_percent=(0.01, 0.1), name="CoarseDropout"),
iaa.Dropout2d(0.1, name="Dropout2d"),
iaa.TotalDropout(0.1, name="TotalDropout"),
iaa.ReplaceElementwise((0.01, 0.05), (0, 255), name="ReplaceElementwise"),
#iaa.ReplaceElementwise((0.95, 0.99), (0, 255), name="ReplaceElementwise"),
iaa.SaltAndPepper((0.01, 0.05), name="SaltAndPepper"),
iaa.ImpulseNoise((0.01, 0.05), name="ImpulseNoise"),
iaa.CoarseSaltAndPepper((0.01, 0.05), size_percent=(0.01, 0.1), name="CoarseSaltAndPepper"),
iaa.Salt((0.01, 0.05), name="Salt"),
iaa.CoarseSalt((0.01, 0.05), size_percent=(0.01, 0.1), name="CoarseSalt"),
iaa.Pepper((0.01, 0.05), name="Pepper"),
iaa.CoarsePepper((0.01, 0.05), size_percent=(0.01, 0.1), name="CoarsePepper"),
iaa.Invert(0.1, name="Invert"),
# ContrastNormalization
iaa.JpegCompression((50, 99), name="JpegCompression")
]
augmenters_artistic = [
iaa.Cartoon(name="Cartoon")
]
augmenters_blend = [
iaa.BlendAlpha((0.01, 0.99), iaa.Identity(), name="Alpha"),
iaa.BlendAlphaElementwise((0.01, 0.99), iaa.Identity(), name="AlphaElementwise"),
iaa.BlendAlphaSimplexNoise(iaa.Identity(), name="SimplexNoiseAlpha"),
iaa.BlendAlphaFrequencyNoise((-2.0, 2.0), iaa.Identity(), name="FrequencyNoiseAlpha"),
iaa.BlendAlphaSomeColors(iaa.Identity(), name="BlendAlphaSomeColors"),
iaa.BlendAlphaHorizontalLinearGradient(iaa.Identity(), name="BlendAlphaHorizontalLinearGradient"),
iaa.BlendAlphaVerticalLinearGradient(iaa.Identity(), name="BlendAlphaVerticalLinearGradient"),
iaa.BlendAlphaRegularGrid(nb_rows=(2, 8), nb_cols=(2, 8), foreground=iaa.Identity(), name="BlendAlphaRegularGrid"),
iaa.BlendAlphaCheckerboard(nb_rows=(2, 8), nb_cols=(2, 8), foreground=iaa.Identity(), name="BlendAlphaCheckerboard"),
# TODO BlendAlphaSegMapClassId
# TODO BlendAlphaBoundingBoxes
]
augmenters_blur = [
iaa.GaussianBlur(sigma=(1.0, 5.0), name="GaussianBlur"),
iaa.AverageBlur(k=(3, 11), name="AverageBlur"),
iaa.MedianBlur(k=(3, 11), name="MedianBlur"),
iaa.BilateralBlur(d=(3, 11), name="BilateralBlur"),
iaa.MotionBlur(k=(3, 11), name="MotionBlur"),
iaa.MeanShiftBlur(spatial_radius=(5.0, 40.0), color_radius=(5.0, 40.0),
name="MeanShiftBlur")
]
augmenters_collections = [
iaa.RandAugment(n=2, m=(6, 12), name="RandAugment")
]
augmenters_color = [
# InColorspace (deprecated)
iaa.WithColorspace(to_colorspace="HSV", children=iaa.Noop(), name="WithColorspace"),
iaa.WithBrightnessChannels(iaa.Identity(), name="WithBrightnessChannels"),
iaa.MultiplyAndAddToBrightness(mul=(0.7, 1.3), add=(-30, 30), name="MultiplyAndAddToBrightness"),
iaa.MultiplyBrightness((0.7, 1.3), name="MultiplyBrightness"),
iaa.AddToBrightness((-30, 30), name="AddToBrightness"),
iaa.WithHueAndSaturation(children=iaa.Noop(), name="WithHueAndSaturation"),
iaa.MultiplyHueAndSaturation((0.8, 1.2), name="MultiplyHueAndSaturation"),
iaa.MultiplyHue((-1.0, 1.0), name="MultiplyHue"),
iaa.MultiplySaturation((0.8, 1.2), name="MultiplySaturation"),
iaa.RemoveSaturation((0.01, 0.99), name="RemoveSaturation"),
iaa.AddToHueAndSaturation((-10, 10), name="AddToHueAndSaturation"),
iaa.AddToHue((-10, 10), name="AddToHue"),
iaa.AddToSaturation((-10, 10), name="AddToSaturation"),
iaa.ChangeColorspace(to_colorspace="HSV", name="ChangeColorspace"),
iaa.Grayscale((0.01, 0.99), name="Grayscale"),
iaa.KMeansColorQuantization((2, 16), name="KMeansColorQuantization"),
iaa.UniformColorQuantization((2, 16), name="UniformColorQuantization"),
iaa.UniformColorQuantizationToNBits((1, 7), name="UniformQuantizationToNBits"),
iaa.Posterize((1, 7), name="Posterize")
]
augmenters_contrast = [
iaa.GammaContrast(gamma=(0.5, 2.0), name="GammaContrast"),
iaa.SigmoidContrast(gain=(5, 20), cutoff=(0.25, 0.75), name="SigmoidContrast"),
iaa.LogContrast(gain=(0.7, 1.0), name="LogContrast"),
iaa.LinearContrast((0.5, 1.5), name="LinearContrast"),
iaa.AllChannelsCLAHE(clip_limit=(2, 10), tile_grid_size_px=(3, 11), name="AllChannelsCLAHE"),
iaa.CLAHE(clip_limit=(2, 10), tile_grid_size_px=(3, 11), to_colorspace="HSV", name="CLAHE"),
iaa.AllChannelsHistogramEqualization(name="AllChannelsHistogramEqualization"),
iaa.HistogramEqualization(to_colorspace="HSV", name="HistogramEqualization"),
]
augmenters_convolutional = [
iaa.Convolve(np.float32([[0, 0, 0], [0, 1, 0], [0, 0, 0]]), name="Convolve_3x3"),
iaa.Sharpen(alpha=(0.01, 0.99), lightness=(0.5, 2), name="Sharpen"),
iaa.Emboss(alpha=(0.01, 0.99), strength=(0, 2), name="Emboss"),
iaa.EdgeDetect(alpha=(0.01, 0.99), name="EdgeDetect"),
iaa.DirectedEdgeDetect(alpha=(0.01, 0.99), name="DirectedEdgeDetect")
]
augmenters_edges = [
iaa.Canny(alpha=(0.01, 0.99), name="Canny")
]
augmenters_flip = [
iaa.Fliplr(1.0, name="Fliplr"),
iaa.Flipud(1.0, name="Flipud")
]
augmenters_geometric = [
iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10),
shear=(-10, 10), order=0, mode="constant", cval=(0, 255), name="Affine_order_0_constant"),
iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10),
shear=(-10, 10), order=1, mode="constant", cval=(0, 255), name="Affine_order_1_constant"),
iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10),
shear=(-10, 10), order=3, mode="constant", cval=(0, 255), name="Affine_order_3_constant"),
iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10),
shear=(-10, 10), order=1, mode="edge", cval=(0, 255), name="Affine_order_1_edge"),
iaa.Affine(scale=(0.9, 1.1), translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)}, rotate=(-10, 10),
shear=(-10, 10), order=1, mode="constant", cval=(0, 255), backend="skimage",
name="Affine_order_1_constant_skimage"),
iaa.PiecewiseAffine(scale=(0.01, 0.05), nb_rows=4, nb_cols=4, order=1, mode="constant",
name="PiecewiseAffine_4x4_order_1_constant"),
iaa.PiecewiseAffine(scale=(0.01, 0.05), nb_rows=4, nb_cols=4, order=0, mode="constant",
name="PiecewiseAffine_4x4_order_0_constant"),
iaa.PiecewiseAffine(scale=(0.01, 0.05), nb_rows=4, nb_cols=4, order=1, mode="edge",
name="PiecewiseAffine_4x4_order_1_edge"),
iaa.PiecewiseAffine(scale=(0.01, 0.05), nb_rows=8, nb_cols=8, order=1, mode="constant",
name="PiecewiseAffine_8x8_order_1_constant"),
iaa.PerspectiveTransform(scale=(0.01, 0.05), keep_size=False, name="PerspectiveTransform"),
iaa.PerspectiveTransform(scale=(0.01, 0.05), keep_size=True, name="PerspectiveTransform_keep_size"),
iaa.ElasticTransformation(alpha=(1, 10), sigma=(0.5, 1.5), order=0, mode="constant", cval=0,
name="ElasticTransformation_order_0_constant"),
iaa.ElasticTransformation(alpha=(1, 10), sigma=(0.5, 1.5), order=1, mode="constant", cval=0,
name="ElasticTransformation_order_1_constant"),
iaa.ElasticTransformation(alpha=(1, 10), sigma=(0.5, 1.5), order=1, mode="nearest", cval=0,
name="ElasticTransformation_order_1_nearest"),
iaa.ElasticTransformation(alpha=(1, 10), sigma=(0.5, 1.5), order=1, mode="reflect", cval=0,
name="ElasticTransformation_order_1_reflect"),
iaa.Rot90((1, 3), keep_size=False, name="Rot90"),
iaa.Rot90((1, 3), keep_size=True, name="Rot90_keep_size"),
iaa.WithPolarWarping(iaa.Identity(), name="WithPolarWarping"),
iaa.Jigsaw(nb_rows=(3, 8), nb_cols=(3, 8), max_steps=1, name="Jigsaw")
]
augmenters_pooling = [
iaa.AveragePooling(kernel_size=(1, 16), keep_size=False, name="AveragePooling"),
iaa.AveragePooling(kernel_size=(1, 16), keep_size=True, name="AveragePooling_keep_size"),
iaa.MaxPooling(kernel_size=(1, 16), keep_size=False, name="MaxPooling"),
iaa.MaxPooling(kernel_size=(1, 16), keep_size=True, name="MaxPooling_keep_size"),
iaa.MinPooling(kernel_size=(1, 16), keep_size=False, name="MinPooling"),
iaa.MinPooling(kernel_size=(1, 16), keep_size=True, name="MinPooling_keep_size"),
iaa.MedianPooling(kernel_size=(1, 16), keep_size=False, name="MedianPooling"),
iaa.MedianPooling(kernel_size=(1, 16), keep_size=True, name="MedianPooling_keep_size")
]
augmenters_imgcorruptlike = [
iaa.imgcorruptlike.GaussianNoise(severity=(1, 5), name="imgcorruptlike.GaussianNoise"),
iaa.imgcorruptlike.ShotNoise(severity=(1, 5), name="imgcorruptlike.ShotNoise"),
iaa.imgcorruptlike.ImpulseNoise(severity=(1, 5), name="imgcorruptlike.ImpulseNoise"),
iaa.imgcorruptlike.SpeckleNoise(severity=(1, 5), name="imgcorruptlike.SpeckleNoise"),
iaa.imgcorruptlike.GaussianBlur(severity=(1, 5), name="imgcorruptlike.GaussianBlur"),
iaa.imgcorruptlike.GlassBlur(severity=(1, 5), name="imgcorruptlike.GlassBlur"),
iaa.imgcorruptlike.DefocusBlur(severity=(1, 5), name="imgcorruptlike.DefocusBlur"),
iaa.imgcorruptlike.MotionBlur(severity=(1, 5), name="imgcorruptlike.MotionBlur"),
iaa.imgcorruptlike.ZoomBlur(severity=(1, 5), name="imgcorruptlike.ZoomBlur"),
iaa.imgcorruptlike.Fog(severity=(1, 5), name="imgcorruptlike.Fog"),
iaa.imgcorruptlike.Frost(severity=(1, 5), name="imgcorruptlike.Frost"),
iaa.imgcorruptlike.Snow(severity=(1, 5), name="imgcorruptlike.Snow"),
iaa.imgcorruptlike.Spatter(severity=(1, 5), name="imgcorruptlike.Spatter"),
iaa.imgcorruptlike.Contrast(severity=(1, 5), name="imgcorruptlike.Contrast"),
iaa.imgcorruptlike.Brightness(severity=(1, 5), name="imgcorruptlike.Brightness"),
iaa.imgcorruptlike.Saturate(severity=(1, 5), name="imgcorruptlike.Saturate"),
iaa.imgcorruptlike.JpegCompression(severity=(1, 5), name="imgcorruptlike.JpegCompression"),
iaa.imgcorruptlike.Pixelate(severity=(1, 5), name="imgcorruptlike.Pixelate"),
iaa.imgcorruptlike.ElasticTransform(severity=(1, 5), name="imgcorruptlike.ElasticTransform")
]
augmenters_pillike = [
iaa.pillike.Solarize(p=1.0, threshold=(32, 128), name="pillike.Solarize"),
iaa.pillike.Posterize((1, 7), name="pillike.Posterize"),
iaa.pillike.Equalize(name="pillike.Equalize"),
iaa.pillike.Autocontrast(name="pillike.Autocontrast"),
iaa.pillike.EnhanceColor((0.0, 3.0), name="pillike.EnhanceColor"),
iaa.pillike.EnhanceContrast((0.0, 3.0), name="pillike.EnhanceContrast"),
iaa.pillike.EnhanceBrightness((0.0, 3.0), name="pillike.EnhanceBrightness"),
iaa.pillike.EnhanceSharpness((0.0, 3.0), name="pillike.EnhanceSharpness"),
iaa.pillike.FilterBlur(name="pillike.FilterBlur"),
iaa.pillike.FilterSmooth(name="pillike.FilterSmooth"),
iaa.pillike.FilterSmoothMore(name="pillike.FilterSmoothMore"),
iaa.pillike.FilterEdgeEnhance(name="pillike.FilterEdgeEnhance"),
iaa.pillike.FilterEdgeEnhanceMore(name="pillike.FilterEdgeEnhanceMore"),
iaa.pillike.FilterFindEdges(name="pillike.FilterFindEdges"),
iaa.pillike.FilterContour(name="pillike.FilterContour"),
iaa.pillike.FilterEmboss(name="pillike.FilterEmboss"),
iaa.pillike.FilterSharpen(name="pillike.FilterSharpen"),
iaa.pillike.FilterDetail(name="pillike.FilterDetail"),
iaa.pillike.Affine(scale=(0.9, 1.1),
translate_percent={"x": (-0.05, 0.05), "y": (-0.05, 0.05)},
rotate=(-10, 10),
shear=(-10, 10),
fillcolor=(0, 255),
name="pillike.Affine"),
]
augmenters_segmentation = [
iaa.Superpixels(p_replace=(0.05, 1.0), n_segments=(10, 100), max_size=64, interpolation="cubic",
name="Superpixels_max_size_64_cubic"),
iaa.Superpixels(p_replace=(0.05, 1.0), n_segments=(10, 100), max_size=64, interpolation="linear",
name="Superpixels_max_size_64_linear"),
iaa.Superpixels(p_replace=(0.05, 1.0), n_segments=(10, 100), max_size=128, interpolation="linear",
name="Superpixels_max_size_128_linear"),
iaa.Superpixels(p_replace=(0.05, 1.0), n_segments=(10, 100), max_size=224, interpolation="linear",
name="Superpixels_max_size_224_linear"),
iaa.UniformVoronoi(n_points=(250, 1000), name="UniformVoronoi"),
iaa.RegularGridVoronoi(n_rows=(16, 31), n_cols=(16, 31), name="RegularGridVoronoi"),
iaa.RelativeRegularGridVoronoi(n_rows_frac=(0.07, 0.14), n_cols_frac=(0.07, 0.14), name="RelativeRegularGridVoronoi"),
]
augmenters_size = [
iaa.Resize((0.8, 1.2), interpolation="nearest", name="Resize_nearest"),
iaa.Resize((0.8, 1.2), interpolation="linear", name="Resize_linear"),
iaa.Resize((0.8, 1.2), interpolation="cubic", name="Resize_cubic"),
iaa.CropAndPad(percent=(-0.2, 0.2), pad_mode="constant", pad_cval=(0, 255), keep_size=False,
name="CropAndPad"),
iaa.CropAndPad(percent=(-0.2, 0.2), pad_mode="edge", pad_cval=(0, 255), keep_size=False,
name="CropAndPad_edge"),
iaa.CropAndPad(percent=(-0.2, 0.2), pad_mode="constant", pad_cval=(0, 255), name="CropAndPad_keep_size"),
iaa.Pad(percent=(0.05, 0.2), pad_mode="constant", pad_cval=(0, 255), keep_size=False, name="Pad"),
iaa.Pad(percent=(0.05, 0.2), pad_mode="edge", pad_cval=(0, 255), keep_size=False, name="Pad_edge"),
iaa.Pad(percent=(0.05, 0.2), pad_mode="constant", pad_cval=(0, 255), name="Pad_keep_size"),
iaa.Crop(percent=(0.05, 0.2), keep_size=False, name="Crop"),
iaa.Crop(percent=(0.05, 0.2), name="Crop_keep_size"),
iaa.PadToFixedSize(width=width+10, height=height+10, pad_mode="constant", pad_cval=(0, 255),
name="PadToFixedSize"),
iaa.CropToFixedSize(width=width-10, height=height-10, name="CropToFixedSize"),
iaa.KeepSizeByResize(iaa.CropToFixedSize(height=height-10, width=width-10), interpolation="nearest",
name="KeepSizeByResize_CropToFixedSize_nearest"),
iaa.KeepSizeByResize(iaa.CropToFixedSize(height=height-10, width=width-10), interpolation="linear",
name="KeepSizeByResize_CropToFixedSize_linear"),
iaa.KeepSizeByResize(iaa.CropToFixedSize(height=height-10, width=width-10), interpolation="cubic",
name="KeepSizeByResize_CropToFixedSize_cubic"),
]
augmenters_weather = [
iaa.FastSnowyLandscape(lightness_threshold=(100, 255), lightness_multiplier=(1.0, 4.0),
name="FastSnowyLandscape"),
iaa.Clouds(name="Clouds"),
iaa.Fog(name="Fog"),
iaa.CloudLayer(intensity_mean=(196, 255), intensity_freq_exponent=(-2.5, -2.0), intensity_coarse_scale=10,
alpha_min=0, alpha_multiplier=(0.25, 0.75), alpha_size_px_max=(2, 8),
alpha_freq_exponent=(-2.5, -2.0), sparsity=(0.8, 1.0), density_multiplier=(0.5, 1.0),
name="CloudLayer"),
iaa.Snowflakes(name="Snowflakes"),
iaa.SnowflakesLayer(density=(0.005, 0.075), density_uniformity=(0.3, 0.9),
flake_size=(0.2, 0.7), flake_size_uniformity=(0.4, 0.8),
angle=(-30, 30), speed=(0.007, 0.03),
blur_sigma_fraction=(0.0001, 0.001), name="SnowflakesLayer"),
iaa.Rain(name="Rain"),
iaa.RainLayer(density=(0.03, 0.14),
density_uniformity=(0.8, 1.0),
drop_size=(0.01, 0.02),
drop_size_uniformity=(0.2, 0.5),
angle=(-15, 15),
speed=(0.04, 0.20),
blur_sigma_fraction=(0.001, 0.001),
name="RainLayer")
]
augmenters = (
augmenters_meta
+ augmenters_arithmetic
+ augmenters_artistic
+ augmenters_blend
+ augmenters_blur
+ augmenters_collections
+ augmenters_color
+ augmenters_contrast
+ augmenters_convolutional
+ augmenters_edges
+ augmenters_flip
+ augmenters_geometric
+ augmenters_pooling
+ augmenters_imgcorruptlike
+ augmenters_pillike
+ augmenters_segmentation
+ augmenters_size
+ augmenters_weather
)
if only_augmenters is not None:
augmenters_reduced = []
for augmenter in augmenters:
if any([re.search(pattern, augmenter.name) for pattern in only_augmenters]):
augmenters_reduced.append(augmenter)
augmenters = augmenters_reduced
return augmenters
def __init__(self, Brightness_ratio=None):
self.Brightness_ratio = Brightness_ratio
self.seq = iaa.Sequential([iaa.MultiplyBrightness((0.95, 1.05))])
#heatmap =heatmap[:,:,:,0]
#plt.imshow(heatmap, cmap='gray')
#plt.show()
aug_list = iaa.OneOf([
<<<<<<< Updated upstream
#iaa.Dropout([0.02, 0.1]),
#iaa.Sharpen((0.0, 1.0)),
iaa.MultiplyHue((0.7, 1.4)),
#iaa.MultiplyBrightness((0.7, 1.4))
=======
iaa.Dropout([0.02, 0.1]),
iaa.Sharpen((0.0, 1.0)),
iaa.MultiplyHue((0.7, 1.4)),
iaa.MultiplyBrightness((0.7, 1.4))
>>>>>>> Stashed changes
])
aug = iaa.Sequential([aug_list, iaa.Fliplr(0.5)], random_order=True)
proc, hm= aug.augment(image=proc_image, heatmaps=heatmap)
hm = hm[0,:,:,0]
plt.imshow(hm, cmap='gray')
plt.show()
imageio.imwrite("example_segmaps.jpg", proc)
def gen_faker_card_run():
path_save = '/home/simple/mydemo/ocr_project/idcard_generator_project/split_text_idcard/'
path = '/home/simple/mydemo/ocr_project/idcard_generator_project/generator_datas1/'
labels = csv.reader(
open(
'/home/simple/mydemo/ocr_project/idcard_generator_project/idcard_generator/src/generate_labels1.csv'
))
# font_template = json.load(open(
# '/home/simple/mydemo/ocr_project/idcard_generator_project/idcard_generator/split_text_template/0adyypn1yq_1.json'))
# xingming = font_template['shapes'][0]['points']
# xingbie = font_template['shapes'][1]['points']
# mingzhu = font_template['shapes'][2]['points']
# chusheng = font_template['shapes'][3]['points']
# dizhi = font_template['shapes'][4]['points']
# shengfengzhenghao = font_template['shapes'][5]['points']
# back_template = json.load(open(
# '/home/simple/mydemo/ocr_project/idcard_generator_project/idcard_generator/image_match/back1.json'))
# qianfajiguang = back_template['shapes'][0]['points']
# youxiaoqixian = back_template['shapes'][1]['points']
font_template = json.load(
open(
'/home/simple/mydemo/ocr_project/idcard_generator_project/idcard_generator/image_match/front.json'
))
xingming = font_template['shapes'][0]['points']
xingbie = font_template['shapes'][1]['points']
mingzhu = font_template['shapes'][2]['points']
chusheng_year = font_template['shapes'][3]['points']
chusheng_month = font_template['shapes'][4]['points']
chusheng_day = font_template['shapes'][5]['points']
dizhi_line1 = font_template['shapes'][6]['points']
dizhi_line2 = font_template['shapes'][7]['points']
dizhi_line3 = font_template['shapes'][8]['points']
shengfengzhenghao = font_template['shapes'][9]['points']
back_template = json.load(
open(
'/home/simple/mydemo/ocr_project/idcard_generator_project/idcard_generator/image_match/back1.json'
))
qianfajiguang1 = back_template['shapes'][1]['points']
qianfajiguang2 = back_template['shapes'][2]['points']
youxiaoqixian = back_template['shapes'][0]['points']
aug_brightness = iaa.MultiplyBrightness((0.5, 1.))
aug_gaussian = iaa.GaussianBlur((0, 2.0))
# blur images with a sigma between 0 and 3.0
csv_file = open(ori_csv_file, 'r', encoding='UTF-8')
csv_reader_lines = list(csv.reader(csv_file))
csv_reader_lines_train, csv_reader_lines_val = train_test_split(
csv_reader_lines, test_size=0.005, random_state=0) # 逐行读取csv文件
date = [] # 创建列表准备接收csv各行数据
cnt = 0 # 记录csv文件行数
path = '/home/simple/mydemo/ocr_project/idcard_generator_project/idcard_generator/template/'
files = os.listdir(os.path.join(path, 'fuzhiwuxiao_mask'))
for one_line in csv_reader_lines_train:
date.append(one_line)
image_name = date[cnt][0]
result_front = []
result_back = []
result_front.append(date[cnt][1]) # 姓名
result_front.append(date[cnt][3]) # 性别
result_front.append(date[cnt][2]) # 名族
result_front.append(date[cnt][4]) # 年
result_front.append(date[cnt][5]) # 月
result_front.append(date[cnt][6]) # 日
result_front.append(date[cnt][7]) # 地址
result_front.append(date[cnt][8]) # 身份号
result_back.append(date[cnt][9]) # 签发机关
result_back.append(date[cnt][10]) # 有效日期
image1 = cv2.imread(front_img) # 读取正面模板
image2 = cv2.imread(back_img) # 读取背面模板
#img_new_white1 = img_to_white(image1)
img_new_white1 = image1
# cv2.imshow('hjs',img_new_white1)
# cv2.waitKey(0)# 生成画布
img_res_f = gen_card_front(img_new_white1, result_front)
img_res_f = cv2.cvtColor(img_res_f, cv2.COLOR_BGR2GRAY)
# 写入文字
#cv2.imwrite(result_card_path + '/{}_1.jpg'.format(image_name), img_res_f)
#img_new_white2 = img_to_white(image2)
img_new_white2 = image2
img_res_b = gen_card_back(img_new_white2, result_back)
img_res_b = cv2.cvtColor(img_res_b, cv2.COLOR_BGR2GRAY)
#cv2.imwrite(result_card_path + '/{}_0.jpg'.format(image_name), img_res_b)
cnt = cnt + 1
print(cnt)
# os.mkdir(path_save + image_name)
for i in range(4):
l = len(files)
index = np.random.randint(0, l)
image_gen_copy = img_res_f.copy()
aug_brightness_deterministic = aug_brightness.to_deterministic()
aug_gaussian_deterministic = aug_gaussian.to_deterministic()
image_gen_copy = np.stack(
[image_gen_copy, image_gen_copy, image_gen_copy], axis=2)
image_gen_copy = aug_brightness_deterministic.augment_images(
images=[image_gen_copy])[0]
image_gen_copy = aug_gaussian_deterministic.augment_images(
images=[image_gen_copy])[0][:, :, 0]
xingming_rect = image_gen_copy[
int(xingming[0][1]):int(xingming[1][1]),
int(xingming[0][0]):int(xingming[1][0])]
xingbie_rect = image_gen_copy[
int(xingbie[0][1]):int(xingbie[1][1]),
int(xingbie[0][0]):int(xingbie[1][0])]
mingzhu_rect = image_gen_copy[
int(mingzhu[0][1]):int(mingzhu[1][1]),
int(mingzhu[0][0]):int(mingzhu[1][0])]
chusheng_rect_year = image_gen_copy[
int(chusheng_year[0][1]):int(chusheng_year[1][1]),
int(chusheng_year[0][0]):int(chusheng_year[1][0])]
chusheng_rect_month = image_gen_copy[
int(chusheng_month[0][1]):int(chusheng_month[1][1]),
int(chusheng_month[0][0]):int(chusheng_month[1][0])]
chusheng_rect_day = image_gen_copy[
int(chusheng_day[0][1]):int(chusheng_day[1][1]),
int(chusheng_day[0][0]):int(chusheng_day[1][0])]
dizhi_rect_line1 = image_gen_copy[
int(dizhi_line1[0][1]):int(dizhi_line1[1][1]),
int(dizhi_line1[0][0]):int(dizhi_line1[1][0])]
dizhi_rect_line2 = image_gen_copy[
int(dizhi_line2[0][1] + 2):int(dizhi_line2[1][1]),
int(dizhi_line2[0][0]):int(dizhi_line2[1][0])]
dizhi_rect_line3 = image_gen_copy[
int(dizhi_line3[0][1] + 3):int(dizhi_line3[1][1]),
int(dizhi_line3[0][0]):int(dizhi_line3[1][0])]
shengfengzhenghao_rect = image_gen_copy[
int(shengfengzhenghao[0][1]):int(shengfengzhenghao[1][1]),
int(shengfengzhenghao[0][0] + 5):int(shengfengzhenghao[1][0])]
cv2.imshow('xingming_roi', xingming_rect)
cv2.imshow('xingbie_roi', xingbie_rect)
cv2.imshow('mingzhu_roi', mingzhu_rect)
cv2.imshow('chusheng_year_roi', chusheng_rect_year)
cv2.imshow('chusheng_month_roi', chusheng_rect_month)
cv2.imshow('chusheng_day_roi', chusheng_rect_day)
cv2.imshow('dizhi_line1_roi', dizhi_rect_line1)
cv2.imshow('dizhi_line2_roi', dizhi_rect_line2)
cv2.imshow('dizhi_line3_roi', dizhi_rect_line3)
cv2.imshow('shengfengzhenghao_roi', shengfengzhenghao_rect)
cv2.waitKey(1000)
# cv2.imwrite(path_save+image_name+'/'+'xingming_rect'+'-'+str(i)+'.jpg',xingming_rect)
# cv2.imwrite(path_save + image_name + '/' + 'dizhi_rect' + '-' + str(i) + '.jpg', dizhi_rect)
# cv2.imwrite(path_save + image_name + '/' + 'xingbie_rect' + '-' + str(i) + '.jpg', xingbie_rect)
# cv2.imwrite(path_save + image_name + '/' + 'mingzhu_rect' + '-' + str(i) + '.jpg', mingzhu_rect)
# cv2.imwrite(path_save + image_name + '/' + 'shengfengzhenghao_rect' + '-' + str(i) + '.jpg', shengfengzhenghao_rect)
# cv2.imwrite(path_save + image_name + '/' + 'chusheng_rect_year' + '-' + str(i) + '.jpg', chusheng_rect_year)
# cv2.imwrite(path_save + image_name + '/' + 'chusheng_rect_month' + '-' + str(i) + '.jpg',
# chusheng_rect_month)
# cv2.imwrite(path_save + image_name + '/' + 'chusheng_rect_day' + '-' + str(i) + '.jpg',
# chusheng_rect_day)
for i in range(4):
l = len(files)
index = np.random.randint(0, l)
image_gen_copy = img_res_b.copy()
aug_brightness_deterministic = aug_brightness.to_deterministic()
aug_gaussian_deterministic = aug_gaussian.to_deterministic()
image_gen_copy = np.stack(
[image_gen_copy, image_gen_copy, image_gen_copy], axis=2)
image_gen_copy = aug_brightness_deterministic.augment_images(
images=[image_gen_copy])[0]
image_gen_copy = aug_gaussian_deterministic.augment_images(
images=[image_gen_copy])[0][:, :, 0]
qianfajiguang1_roi = image_gen_copy[
int(qianfajiguang1[0][1]):int(qianfajiguang1[1][1]),
int(qianfajiguang1[0][0]):int(qianfajiguang1[1][0])]
qianfajiguang2_roi = image_gen_copy[
int(qianfajiguang2[0][1] - 3):int(qianfajiguang2[1][1] - 3),
int(qianfajiguang2[0][0]):int(qianfajiguang2[1][0])]
youxiaoqixian_roi = image_gen_copy[
int(youxiaoqixian[0][1]):int(youxiaoqixian[1][1]),
int(youxiaoqixian[0][0]):int(youxiaoqixian[1][0])]
cv2.imshow('qianfajiguang1_roi', qianfajiguang1_roi)
cv2.imshow('qianfajiguang2_roi', qianfajiguang2_roi)
cv2.imshow('youxiaoqixian_roi', youxiaoqixian_roi)
cv2.waitKey(1000)
def __getitem__(self, index):
assert index <= self.nSamples, 'index range error'
index += 1
try:
img_root_i = osp.join(self.data_root, str(index) + '.txt')
with open(img_root_i, 'r') as f:
lines = f.readlines()
js_p = lines[0].strip()
img_p = lines[1].strip()
img = Image.open(img_p)
img = img.convert("RGB")
except IOError:
print('Corrupted image for %d' % index)
return self[index + 1]
ori_w, ori_h = img.size
img = img.resize((self.width, self.height))
try:
pt = fileutils.red_json(js_p)
pt[0] = pt[0] / ori_w * self.width
pt[1] = pt[1] / ori_h * self.height
except IndexError:
return self[index + 1]
pt_x = pt[0]
pt_y = pt[1]
# fileutils.test_point(img,pt[0],pt[1],index,tag='ori')
if self.is_train:
self.augment = iaa.Sequential([
iaa.MotionBlur(k=5, angle=45),
iaa.CropAndPad(percent=(-0.2, 0.2), pad_mode="edge"),
iaa.AdditiveGaussianNoise(scale=(0, 0.05 * 255)),
iaa.SaltAndPepper(0.2, per_channel=True),
iaa.AddToHueAndSaturation((-60, 60)),
iaa.MultiplyBrightness((0.5, 1.5)),
iaa.Affine(rotate=(-180, 180)),
iaa.pillike.EnhanceSharpness(),
iaa.pillike.EnhanceColor(),
iaa.Dropout(p=(0, 0.1))
],
random_order=True)
kps = [
ia.Keypoint(x=pt[0], y=pt[1]),
]
if random.uniform(0, 1) < 0.2:
pt_x = pt[0]
pt_y = pt[1]
else:
img = np.asarray(img, dtype=np.uint8)
kpsoi = ia.KeypointsOnImage(kps, shape=img.shape)
aug_det = self.augment.to_deterministic()
img = aug_det.augment_image(img)
pt_aug = aug_det.augment_keypoints(kpsoi)
# img = self.augment(image = img)
img = Image.fromarray(img)
pt_x = pt_aug[0].x_int
pt_y = pt_aug[0].y_int
# fileutils.test_point(img,pt_x,pt_y,index)
# img.save('seeee_'+str(index)+'_.jpg')
if self.transform is not None:
img = self.transform(img)
return img, pt_x, pt_y
