def apply_equalize(input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
r"""Equalize an image.
Args:
input (torch.Tensor): Tensor to be transformed with shape :math:`(*, C, H, W)`.
Returns:
torch.Tensor: Adjusted image with shape :math:`(B, C, H, W)`.
"""
return equalize(input)
def apply_equalize(input: torch.Tensor,
params: Dict[str, torch.Tensor]) -> torch.Tensor:
r"""Equalize an image.
Args:
input (torch.Tensor): Tensor to be transformed with shape (H, W), (C, H, W), (B, C, H, W).
Returns:
torch.Tensor: Adjusted image.
"""
input = _transform_input(input)
_validate_input_dtype(
input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
return equalize(input)
def apply_equalize(input: torch.Tensor, params: Dict[str, torch.Tensor]) -> torch.Tensor:
r"""Equalize 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['p']: Probability.
Returns:
torch.Tensor: Adjusted image.
"""
input = _transform_input(input)
_validate_input_dtype(input, accepted_dtypes=[torch.float16, torch.float32, torch.float64])
res = []
for image, prob in zip(input, params['batch_prob']):
res.append(equalize(image) if prob else image)
return torch.cat(res, dim=0)
def add_equal(img, x):
img_norm = img / torch.max(img)
img_eq = equalize(img_norm)
return torch.lerp(img_norm, img_eq, x)
def apply_transform(self,
input: Tensor,
params: Dict[str, Tensor],
transform: Optional[Tensor] = None) -> Tensor:
return equalize(input)