class RandomSizedCrop_64_512(BenchmarkTest):
def __init__(self):
self.augmentor_pipeline = Pipeline()
self.augmentor_pipeline.add_operation(
Operations.Crop(probability=1, width=64, height=64, centre=False))
self.augmentor_pipeline.add_operation(
Operations.Resize(probability=1,
width=512,
height=512,
resample_filter="BILINEAR"))
self.imgaug_transform = iaa.Sequential([
iaa.CropToFixedSize(width=64, height=64),
iaa.Scale(size=512, interpolation="linear")
])
self.solt_stream = slc.Stream([
slt.CropTransform(crop_size=(64, 64), crop_mode="r"),
slt.ResizeTransform(resize_to=(512, 512))
])
def albumentations(self, img):
img = albumentations.random_crop(img,
crop_height=64,
crop_width=64,
h_start=0,
w_start=0)
return albumentations.resize(img, height=512, width=512)
def augmentor(self, img):
for operation in self.augmentor_pipeline.operations:
img, = operation.perform_operation([img])
return np.array(img, np.uint8, copy=True)
def torchvision_transform(self, img):
img = torchvision.crop(img, top=0, left=0, height=64, width=64)
return torchvision.resize(img, (512, 512))
class BrightnessContrast(BenchmarkTest):
def __init__(self):
self.imgaug_transform = iaa.Sequential([
iaa.Multiply((1.5, 1.5), per_channel=False),
iaa.Add((127, 127), per_channel=False)
])
self.augmentor_pipeline = Pipeline()
self.augmentor_pipeline.add_operation(
Operations.RandomBrightness(probability=1,
min_factor=1.5,
max_factor=1.5))
self.augmentor_pipeline.add_operation(
Operations.RandomContrast(probability=1,
min_factor=1.5,
max_factor=1.5))
self.solt_stream = slc.Stream([
slt.ImageRandomBrightness(p=1, brightness_range=(127, 127)),
slt.ImageRandomContrast(p=1, contrast_range=(1.5, 1.5)),
])
def albumentations(self, img):
return albumentations.brightness_contrast_adjust(img,
alpha=1.5,
beta=0.5,
beta_by_max=True)
def torchvision_transform(self, img):
img = torchvision.adjust_brightness(img, brightness_factor=1.5)
img = torchvision.adjust_contrast(img, contrast_factor=1.5)
return img
def augmentor(self, img):
for operation in self.augmentor_pipeline.operations:
img, = operation.perform_operation([img])
return np.array(img, np.uint8, copy=True)
def create_aug_pipeline_val(input_size):
"""Image Augmentation Pipeline for Validation/Test Set."""
p_val = Pipeline()
# # Center Crop
# p_val.crop_centre(probability=1, percentage_area=0.9)
# Resize the image to the desired input size of the model
p_val.resize(probability=1, width=input_size[0], height=input_size[1])
return p_val
def __init__(self, train=True, root='../data'):
if train:
self.dataset = MNIST(root=root, train=True)
else:
self.dataset = MNIST(root=root, train=False)
self.transform = transforms.Compose( [transforms.ToTensor()] )
self.p = Pipeline()
self.p.random_distortion(probability=0.5, grid_width=7, grid_height=7, magnitude=1)
def __init__(self):
self.augmentor_pipeline = Pipeline()
self.augmentor_pipeline.add_operation(Operations.Crop(probability=1, width=64, height=64, centre=False))
self.augmentor_pipeline.add_operation(
Operations.Resize(probability=1, width=512, height=512, resample_filter="BILINEAR")
)
self.imgaug_transform = iaa.Sequential(
[iaa.CropToFixedSize(width=64, height=64), iaa.Scale(size=512, interpolation="linear")]
)
self.solt_stream = slc.Stream(
[slt.CropTransform(crop_size=(64, 64), crop_mode="r"), slt.ResizeTransform(resize_to=(512, 512))]
)
def __init__(self):
self.imgaug_transform = iaa.Sequential(
[iaa.Multiply((1.5, 1.5), per_channel=False), iaa.Add((127, 127), per_channel=False)]
)
self.augmentor_pipeline = Pipeline()
self.augmentor_pipeline.add_operation(
Operations.RandomBrightness(probability=1, min_factor=1.5, max_factor=1.5)
)
self.augmentor_pipeline.add_operation(Operations.RandomContrast(probability=1, min_factor=1.5, max_factor=1.5))
self.solt_stream = slc.Stream(
[
slt.ImageRandomBrightness(p=1, brightness_range=(127, 127)),
slt.ImageRandomContrast(p=1, contrast_range=(1.5, 1.5)),
]
)
class Dataset(data.Dataset):
def __init__(self, train=True, root='../data'):
if train:
self.dataset = MNIST(root=root, train=True)
else:
self.dataset = MNIST(root=root, train=False)
self.transform = transforms.Compose( [transforms.ToTensor()] )
self.p = Pipeline()
self.p.random_distortion(probability=0.5, grid_width=7, grid_height=7, magnitude=1)
def __len__(self,):
return len(self.dataset)
def __getitem__(self, i):
img = self.dataset[i][0]
lab = self.dataset[i][1]
# img = self._sample([img], self.p)[0]
img = self.transform(img)
# img = 2 * (img - 0.5)
lab = torch.eye(10)[lab]
return img, lab
def _sample(self, image, p):
for op in p.operations:
r = round(random.uniform(0, 1), 1)
if r <= op.probability:
image = op.perform_operation(image)
return image
def create_aug_pipeline_train(input_size):
"""Image Augmentation Pipeline for Training Set."""
p_train = Pipeline()
# Random crop
p_train.add_operation(CropPercentageRange(probability=1, min_percentage_area=0.8, max_percentage_area=1, centre=False))
# Rotate the image by either 90, 180, or 270 degrees randomly
p_train.rotate_random_90(probability=0.5)
# Flip the image along its vertical axis
p_train.flip_top_bottom(probability=0.5)
# Flip the image along its horizontal axis
p_train.flip_left_right(probability=0.5)
# Random change brightness of the image
p_train.random_brightness(probability=0.5, min_factor=0.9, max_factor=1.1)
# Random change saturation of the image
p_train.random_color(probability=0.5, min_factor=0.9, max_factor=1.1)
# Resize the image to the desired input size of the model
p_train.resize(probability=1, width=input_size[0], height=input_size[1])
return p_train
png = data.train.images[i]
png = np.array(png, dtype='float')
pixels = png.reshape((28, 28))
image.imsave('image_no_{}.png'.format(i), pixels, cmap='gray')
# In[10]:
print(os.listdir())
# In[11]:
from Augmentor import Pipeline
# In[12]:
augmentor = Pipeline('/home/asherif844/sparkNotebooks/Ch03/MNIST/images')
# In[13]:
augmentor.rotate(probability=0.9, max_left_rotation=25, max_right_rotation=25)
# In[14]:
for i in range(1, 3):
augmentor.sample(10)
# In[15]:
xtrain = data.train.images
ytrain = np.asarray(data.train.labels)
xtest = data.test.images
def make_pipeline(imageset_path, output_dir):
"""returns an augmentation pipeline for a given image set"""
p = Pipeline(imageset_path, output_dir)
p.random_distortion(probability=0.7,
grid_width=4,
grid_height=4,
magnitude=8)
p.flip_left_right(probability=0.5)
p.flip_top_bottom(probability=0.5)
p.zoom(probability=0.3, min_factor=1.1, max_factor=1.4)
p.rotate(probability=0.5, max_left_rotation=10, max_right_rotation=10)
return p
随机20度范围内的旋转。变换时，边界外像素点的填充采用“reflect”模式。图像均被缩放为256*256大小，像素值被调整到0-1之间。 ''' # this is import from Augmentor third-party package # import Augmentor # # # create a new pipeline # file_path = "C:\\liyu\\files\\tiff\\cells" # p = Augmentor.Pipeline(file_path) from Augmentor.Pipeline import * import time # create a new pipeline file_path = "C:\\liyu\\files\\tiff\\newtest" p = Pipeline(file_path) # add operations to the pipeline # 水平翻转 p.flip_left_right(probability=0.8) # # 垂直翻转 # p.flip_top_bottom(probability=0.5) # # # 随机90， 180， 270 度旋转 # p.rotate_random_90(probability=0.75) # # # 随机20度内旋转，不变形, 四角填充黑色，图片大小不变 # p.rotate_without_crop(probability=0.5, max_left_rotation=20, max_right_rotation=20) #
import Augmentor
from Augmentor import Pipeline
p = Augmentor.Pipeline(
"/Users/marc/Desktop/rbg/image"
) # ensure you press enter after this, don't just c&p this code.
p.ground_truth("/Users/marc/Desktop/rbg/gt")
Pipeline.set_seed(100)
p.flip_left_right(probability=0.4)
p.flip_top_bottom(probability=0.4)
p.rotate(probability=0.4, max_left_rotation=25, max_right_rotation=25)
p.random_distortion(probability=0.5, grid_width=6, grid_height=6, magnitude=8)
p.sample(2124)
#
#
# from PIL import Image
# from PIL import ImageFilter
# import os
#
# path, dirs, files = next(os.walk(
# "/Users/marc/Aquisition Images Final/HSL - Ratcliff1 - Polar"))
# path2, dirs2, files2 = next(os.walk(
# "/Users/marc/Aquisition Images Final/GroundTruth"))
#
# out_list = []
# in_list = []
# files_list = []
#
# for file in files:
# if not file.endswith(".png"):
