def __getitem__(self, index):
input = self.images[index % self.len]
if self.augmentations is not None:
input = self.augmentations(input)
if self.crop_size != -1:
# For training, take random crop.
if input.size[0] < self.crop_size or input.size[1] < self.crop_size:
input = input.resize((self.crop_size, self.crop_size), Image.BICUBIC)
else:
input = RandomCrop(self.crop_size)(input)
else:
# For testing, we want to take the whole image.
width, height = input.size[:2]
width = width - (width % self.upscale_factor)
height = height - (height % self.upscale_factor)
input = CenterCrop((height, width))(input)
# Make a high-resolution copy.
target = input.copy()
# Downsample to create image at low-res.
# We already make sure that crop_size divides upscale_factor.
input = input.resize(
(input.size[0]//self.upscale_factor, input.size[1]//self.upscale_factor),
Image.BICUBIC)
# Upsample using bicubic interpolation.
input = input.resize(target.size, Image.BICUBIC)
input = ToTensor()(input)
target = ToTensor()(target)
return input, target
def __getitem__(self, index):
input = self.images[index % self.len]
if self.augmentations is not None:
input = self.augmentations(input)
if self.crop_size != -1:
# For training, take random crop.
if input.size[0] < self.crop_size or input.size[1] < self.crop_size:
input = input.resize((self.crop_size, self.crop_size),
Image.BICUBIC)
else:
input = RandomCrop(self.crop_size)(input)
else:
# For testing, we want to take the whole image.
width, height = input.size[:2]
width = width - (width % self.upscale_factor)
height = height - (height % self.upscale_factor)
input = CenterCrop((height, width))(input)
# LapSRN employs deep supervision, so there will be multiple targets
# (one target at each level).
targets = [input.copy()]
input = input.resize((input.size[0] // 2, input.size[1] // 2),
Image.BICUBIC)
n_levels = int(np.log2(self.upscale_factor))
for i in range(n_levels - 1):
targets = [input] + targets
input = input.resize((input.size[0] // 2, input.size[1] // 2),
Image.BICUBIC)
input = ToTensor()(input)
for i in range(n_levels):
targets[i] = ToTensor()(targets[i])
return input, targets
