def __call__(self, input, target):
## do something to both images
input = Resize((1086, 1351), Image.BILINEAR)(input)
target = Resize((1086, 1351), Image.NEAREST)(target)
#input = Resize((512,1024), Image.BILINEAR)(input)
#target = Resize((512,1024),Image.NEAREST)(target)
if (self.augment):
rotation_degree = 1
shear_degree = 1
input = RandomAffine(rotation_degree,
None,
None,
shear_degree,
resample=Image.BILINEAR,
fillcolor=0)(input)
target = RandomAffine(rotation_degree,
None,
None,
shear_degree,
resample=Image.NEAREST,
fillcolor=255)(target)
w, h = input.size
nratio = random.uniform(0.5, 1.0)
ni = random.randint(0, int(h - nratio * h))
nj = random.randint(0, int(w - nratio * w))
input = input.crop(
(nj, ni, int(nj + nratio * w), int(ni + nratio * h)))
target = target.crop(
(nj, ni, int(nj + nratio * w), int(ni + nratio * h)))
input = Resize((512, 1024), Image.BILINEAR)(input)
target = Resize((512, 1024), Image.NEAREST)(target)
brightness = 0.1
contrast = 0.1
saturation = 0.1
hue = 0.1
input = ColorJitter(brightness, contrast, saturation, hue)(input)
hflip = random.random()
if (hflip < 0.5):
input = input.transpose(Image.FLIP_LEFT_RIGHT)
target = target.transpose(Image.FLIP_LEFT_RIGHT)
else:
input = Resize((512, 1024), Image.BILINEAR)(input)
target = Resize((512, 1024), Image.NEAREST)(target)
input = ToTensor()(input)
if (self.enc):
target = Resize((64, 128), Image.NEAREST)(target)
target = ToLabel()(target)
target = Relabel(255, 27)(target)
return input, target
def __call__(self, input, target):
# do something to both images
input = Scale(self.height, Image.BILINEAR)(input)
target = Scale(self.height, Image.NEAREST)(target)
if(self.augment):
# Random hflip
hflip = random.random()
if (hflip < 0.5):
input = input.transpose(Image.FLIP_LEFT_RIGHT)
target = target.transpose(Image.FLIP_LEFT_RIGHT)
input = ToTensor()(input)
target = ToLabel()(target)
for iter in range(1,19):
target = Relabel(iter, 255)(target)
target = Relabel(19, 1)(target)
target = Relabel(20, 2)(target)
target = Relabel(21, 3)(target)
target = Relabel(22, 4)(target)
target = Relabel(23, 5)(target)
target = Relabel(24, 6)(target)
target = Relabel(25, 7)(target)
target = Relabel(26, 8)(target)
target = Relabel(27, 9)(target)
return input, target
def __call__(self, input, target):
# do something to both images
input = Scale(self.height, Image.BILINEAR)(input)
target = Scale(self.height, Image.NEAREST)(target)
if (self.augment):
# Random hflip
hflip = random.random()
if (hflip < 0.5):
input = input.transpose(Image.FLIP_LEFT_RIGHT)
target = target.transpose(Image.FLIP_LEFT_RIGHT)
#Random translation 0-2 pixels (fill rest with padding
transX = random.randint(-2, 2)
transY = random.randint(-2, 2)
input = ImageOps.expand(input,
border=(transX, transY, 0, 0),
fill=0)
target = ImageOps.expand(target,
border=(transX, transY, 0, 0),
fill=255) #pad label filling with 255
input = input.crop(
(0, 0, input.size[0] - transX, input.size[1] - transY))
target = target.crop(
(0, 0, target.size[0] - transX, target.size[1] - transY))
#TODO future: additional augments
#CenterCrop(256)
#Normalize([.485, .456, .406], [.229, .224, .225]),
input = ToTensor()(input)
if (self.enc):
target = Scale(int(self.height / 8), Image.NEAREST)(target)
target = ToLabel()(target)
target = Relabel(255, 19)(target)
return input, target
cv2.imshow("test", cv_image)
cv2.waitKey(-1)
def showTensorImage(tensor_image):
pil_image = transforms.ToPILImage()(tensor_image).convert('RGB')
showImage(pil_image)
if __name__ == "__main__":
from torchvision.transforms import Compose, CenterCrop, Normalize
from torchvision.transforms import ToTensor, ToPILImage
from piwise.transform import Relabel, ToLabel, Colorize
image_transform = ToPILImage()
input_transform = Compose([
CenterCrop(30),
ToTensor(),
#Normalize([.485, .456, .406], [.229, .224, .225]),
])
target_transform = Compose([
CenterCrop(30),
ToLabel(),
#Relabel(255, 21),
])
dataset = VOC12("/data_1/data/VOC2012/VOCdevkit/VOC2012", input_transform,
target_transform)
for image, label in dataset:
print(label)
#showTensorImage(image)
def __call__(self, input, target):
# do something to both images
input = Scale(self.height, Image.BILINEAR)(input)
target = Scale(self.height, Image.NEAREST)(target)
if (self.augment):
# Random hflip
hflip = random.random()
if (hflip < 0.5):
input = input.transpose(Image.FLIP_LEFT_RIGHT)
target = target.transpose(Image.FLIP_LEFT_RIGHT)
degree = random.randint(-20, 20)
input = input.rotate(degree, resample=Image.BILINEAR, expand=True)
target = target.rotate(degree, resample=Image.NEAREST, expand=True)
w, h = input.size
nratio = random.uniform(0.5, 1.0)
ni = random.randint(0, int(h - nratio * h))
nj = random.randint(0, int(w - nratio * w))
input = input.crop(
(nj, ni, int(nj + nratio * w), int(ni + nratio * h)))
target = target.crop(
(nj, ni, int(nj + nratio * w), int(ni + nratio * h)))
input = Resize((480, 640), Image.BILINEAR)(input)
target = Resize((480, 640), Image.NEAREST)(target)
brightness_factor = random.uniform(0.8, 1.2)
contrast_factor = random.uniform(0.8, 1.2)
saturation_factor = random.uniform(0.8, 1.2)
#sharpness_factor=random.uniform(0.0,2.0)
hue_factor = random.uniform(-0.2, 0.2)
enhancer1 = ImageEnhance.Brightness(input)
input = enhancer1.enhance(brightness_factor)
enhancer2 = ImageEnhance.Contrast(input)
input = enhancer2.enhance(contrast_factor)
enhancer3 = ImageEnhance.Color(input)
input = enhancer3.enhance(saturation_factor)
#enhancer4=ImageEnhance.Sharpness(input)
#input=enhancer4.enhance(sharpness_factor)
input_mode = input.mode
h, s, v = input.convert('HSV').split()
np_h = np.array(h, dtype=np.uint8)
with np.errstate(over='ignore'):
np_h += np.uint8(hue_factor * 255)
h = Image.fromarray(np_h, 'L')
input = Image.merge('HSV', (h, s, v)).convert(input_mode)
else:
input = Resize((480, 640), Image.BILINEAR)(input)
target = Resize((480, 640), Image.NEAREST)(target)
input = ToTensor()(input)
if (self.enc):
target = Resize((60, 80), Image.NEAREST)(target)
target = ToLabel()(target)
target = Relabel(255, 27)(target)
return input, target