def apply_adjust_saturation(input: torch.Tensor,
params: Dict[str, torch.Tensor],
return_transform: bool = False):
"""Wrapper for adjust_saturation for Torchvision-like param settings.
Args:
input (torch.Tensor): Image/Tensor to be adjusted in the shape of (*, N).
saturation_factor (float): How much to adjust the saturation. 0 will give a black
and white image, 1 will give the original image while 2 will enhance the saturation
by a factor of 2.
Returns:
torch.Tensor: Adjusted image.
"""
input = _transform_input(input)
_validate_input_dtype(
input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
transformed = adjust_saturation(
input, params['saturation_factor'].to(input.dtype))
if return_transform:
identity: torch.Tensor = torch.eye(3,
device=input.device,
dtype=input.dtype).repeat(
input.shape[0], 1, 1)
return transformed, identity
return transformed
def apply_adjust_saturation(input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
"""Wrapper for adjust_saturation for Torchvision-like param settings.
Args:
input (torch.Tensor): Image/Tensor to be adjusted in the shape of (*, N).
params (Dict[str, torch.Tensor]):
- params['saturation_factor']: How much to adjust the saturation. 0 will give a black
and white image, 1 will give the original image while 2 will enhance the saturation
by a factor of 2.
Returns:
torch.Tensor: Adjusted image.
"""
input = _transform_input(input)
_validate_input_dtype(input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
transformed = adjust_saturation(input, params['saturation_factor'].to(input.dtype))
return transformed