def apply_adjust_hue(input: torch.Tensor,
params: Dict[str, torch.Tensor]) -> torch.Tensor:
"""Apply hue adjustment.
Wrapper for adjust_hue for Torchvision-like param settings.
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['hue_factor']: How much to shift the hue channel. Should be in [-0.5, 0.5].
0.5 and -0.5 give complete reversal of hue channel in HSV space in positive and negative
direction respectively. 0 means no shift. Therefore, both -0.5 and 0.5 will give an
image with complementary colors while 0 gives the original image.
Returns:
torch.Tensor: Adjusted image.
"""
input = _transform_input(input)
_validate_input_dtype(
input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
transformed = adjust_hue(input,
params['hue_factor'].to(input.dtype) * 2 * pi)
return transformed
def apply_transform(
self, input: Tensor, params: Dict[str, Tensor], transform: Optional[Tensor] = None
) -> Tensor:
transforms = [
lambda img: adjust_brightness(img, params["brightness_factor"] - 1),
lambda img: adjust_contrast(img, params["contrast_factor"]),
lambda img: adjust_saturation(img, params["saturation_factor"]),
lambda img: adjust_hue(img, params["hue_factor"] * 2 * pi),
]
jittered = input
for idx in params["order"].tolist():
t = transforms[idx]
jittered = t(jittered)
return jittered
