def __call__(self, input, target):
# do something to both images
input = Resize(self.height, Image.BILINEAR)(input)
target = Resize(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))
input = ToTensor()(input)
if (self.enc):
target = Resize(int(self.height/8), Image.NEAREST)(target)
target = ToLabel()(target)
target = Relabel(255, 19)(target)
return input, target
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 transform(self, img, lbl):
img = Resize(self.img_size, Image.BILINEAR)(img)
lbl = Resize(self.img_size, Image.NEAREST)(lbl)
if (self.augment):
hflip = random.random()
if (hflip < 0.5):
img = img.transpose(Image.FLIP_LEFT_RIGHT)
lbl = lbl.transpose(Image.FLIP_LEFT_RIGHT)
transX = random.randint(-2, 2)
transY = random.randint(-2, 2)
img = ImageOps.expand(img, border=(transX, transY, 0, 0), fill=0)
lbl = ImageOps.expand(lbl, border=(transX, transY, 0, 0), fill=0)
img = img.crop((0, 0, img.size[0] - transX, img.size[1] - transY))
lbl = lbl.crop((0, 0, lbl.size[0] - transX, lbl.size[1] - transY))
if (self.label_scale):
lbl = Resize([self.img_size[0] // 8, self.img_size[1] // 8],
Image.NEAREST)(lbl)
img = ToTensor()(img)
# img = Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])(img)
lbl = np.array(lbl)
lbl_copy = lbl.copy()
for k, v in self.id_to_trainid.items():
lbl[lbl_copy == k] = v
lbl = torch.from_numpy(lbl).long()
return img, lbl
def __call__(self, input, gray, target):
# do something to both images
if self.height != 8.1:
input = Resize(self.height, Image.BILINEAR)(input)
gray = Resize(self.height, Image.BILINEAR)(gray)
target = Resize(self.height, Image.NEAREST)(target)
# === Data Augmentation === #
if (self.dataAugment):
# 1. Random horizenal flip
hflip = random.random()
if (hflip < 0.5):
input = input.transpose(Image.FLIP_LEFT_RIGHT)
gray = gray.transpose(Image.FLIP_LEFT_RIGHT)
target = target.transpose(Image.FLIP_LEFT_RIGHT)
# 2. 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)
gray = ImageOps.expand(gray, 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))
gray = gray.crop(
(0, 0, gray.size[0] - transX, gray.size[1] - transY))
target = target.crop(
(0, 0, target.size[0] - transX, target.size[1] - transY))
input = ToTensor()(input)
gray = ToTensor()(gray)
if (self.encoderOnly):
target = Resize(int(self.height / 8), Image.NEAREST)(target)
target = ToLabel()(target)
target = Relabel(255, 19)(target) # ignored label 255 -> 19
input = torch.cat((input, gray), 0)
return input, target
def __call__(self, input, input1, target):
# Resizing data to required size
input = Resize((self.height, 320), Image.BILINEAR)(input) #askalex
input1 = Resize((self.height, 320),
Image.BILINEAR)(input1) #ChangedByUs
target = Resize((self.height, 320), Image.NEAREST)(target)
if (self.augment):
# Random horizontal flip
hflip = random.random()
if (hflip < 0.5):
input = input.transpose(Image.FLIP_LEFT_RIGHT)
input1 = input1.transpose(Image.FLIP_LEFT_RIGHT) #ChangedByUs
target = target.transpose(Image.FLIP_LEFT_RIGHT)
#Random translation 0-2 pixels (fill rest with padding)
transX = random.randint(0, 2)
transY = random.randint(0, 2)
input = ImageOps.expand(input,
border=(transX, transY, 0, 0),
fill=0)
input1 = ImageOps.expand(input1,
border=(transX, transY, 0, 0),
fill=0) #ChangedByUs
target = ImageOps.expand(
target, border=(transX, transY, 0, 0),
fill=255) #pad label filling with 7 #askalex- change 255
input = input.crop(
(0, 0, input.size[0] - transX, input.size[1] - transY))
input1 = input1.crop((0, 0, input1.size[0] - transX,
input1.size[1] - transY)) #ChangedByUs
target = target.crop(
(0, 0, target.size[0] - transX, target.size[1] - transY))
input = ToTensor()(input)
input1 = ToTensor()(input1) #ChangedByUs
target = ToLabel()(target)
#target = Relabel(255, 7)(target)
return input, input1, target #ChangedByUs
def __getitem__(self, index):
example = self.examples[index]
img_path = example["img_path"]
label_img_path = example["label_img_path"]
with open(img_path, "rb") as f:
img = Image.open(f).convert("RGB")
with open(label_img_path, "rb") as f:
label_img = Image.open(f).convert("P")
img = Resize(self.new_img_h, Image.BILINEAR)(img)
label_img = Resize(self.new_img_h, Image.NEAREST)(label_img)
if self.mode == "train":
hflip = random.random()
if (hflip < 0.5):
img = img.transpose(Image.FLIP_LEFT_RIGHT)
label_img = label_img.transpose(Image.FLIP_LEFT_RIGHT)
transX = random.randint(-2, 2)
transY = random.randint(-2, 2)
img = ImageOps.expand(img, border=(transX, transY, 0, 0), fill=0)
label_img = ImageOps.expand(label_img,
border=(transX, transY, 0, 0),
fill=255) #pad label filling with 255
img = img.crop((0, 0, img.size[0] - transX, img.size[1] - transY))
label_img = label_img.crop(
(0, 0, label_img.size[0] - transX, label_img.size[1] - transY))
img = self.tran(img)
if self.only_encode:
label_img = Resize(int(self.new_img_h / 8),
Image.NEAREST)(label_img)
label_img = torch.from_numpy(np.array(label_img)).long()
label_img[label_img == 255] = num_classes - 1
return (img, label_img)
