def apply_transform(self,
input: Tensor,
params: Dict[str, Tensor],
transform: Optional[Tensor] = None) -> Tensor:
thresholds = params["thresholds"]
additions: Optional[Tensor]
if "additions" in params:
additions = params["additions"]
else:
additions = None
return solarize(input, thresholds, additions)
def apply_solarize(input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
r"""Solarize an image.
Args:
input (torch.Tensor): Tensor to be transformed with shape :math:`(*, C, H, W)`.
params (Dict[str, torch.Tensor]):
- params['thresholds_factor']: thresholds ranged from 0 ~ 1.
- params['additions_factor']: additions to add on before solarizing.
Returns:
torch.Tensor: Adjusted image with shape :math:`(B, C, H, W)`.
"""
thresholds = params['thresholds_factor']
additions: Optional[torch.Tensor]
if 'additions_factor' in params:
additions = params['additions_factor']
else:
additions = None
return solarize(input, thresholds, additions)
def apply_solarize(input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
r"""Solarize an image.
Args:
input (torch.Tensor): Tensor to be transformed with shape (H, W), (C, H, W), (B, C, H, W).
params (Dict[str, torch.Tensor]):
- params['thresholds_factor']: thresholds ranged from 0 ~ 1.
- params['additions_factor']: additions to add on before solarizing.
Returns:
torch.Tensor: Adjusted image.
"""
input = _transform_input(input)
_validate_input_dtype(input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
thresholds = params['thresholds_factor']
additions: Optional[torch.Tensor]
if 'additions_factor' in params:
additions = params['additions_factor']
else:
additions = None
return solarize(input, thresholds, additions)