def get_transform(train):
base_size = 520
crop_size = 480
return presets.SegmentationPresetTrain(
base_size,
crop_size) if train else presets.SegmentationPresetEval(base_size)
def get_transform(train, args):
if train:
return presets.SegmentationPresetTrain(base_size=520, crop_size=480)
elif not args.weights:
return presets.SegmentationPresetEval(base_size=520)
else:
weights = PM.get_weight(args.weights)
return weights.transforms()
def get_transform(train):
base_size = 520
crop_size = 480
return presets.SegmentationPresetTrain(
base_size, crop_size) if train else presets.SegmentationPresetEval(
base_size,
contrast=args.contrast,
brightness=args.brightness,
sigma=args.sigma)
def get_transform(train, args):
if train:
return presets.SegmentationPresetTrain(base_size=520, crop_size=480)
elif not args.prototype:
return presets.SegmentationPresetEval(base_size=520)
else:
if args.weights:
weights = prototype.models.get_weight(args.weights)
return weights.transforms()
else:
return prototype.transforms.SemanticSegmentationEval(resize_size=520)
def get_transform(train, args):
if train:
return presets.SegmentationPresetTrain(base_size=520, crop_size=480)
elif args.weights and args.test_only:
weights = torchvision.models.get_weight(args.weights)
trans = weights.transforms()
def preprocessing(img, target):
img = trans(img)
size = F.get_dimensions(img)[1:]
target = F.resize(target, size, interpolation=InterpolationMode.NEAREST)
return img, F.pil_to_tensor(target)
return preprocessing
else:
return presets.SegmentationPresetEval(base_size=520)