o oi> @sddlmZddlmZddlmZmZddlmZm Z dedee efdedee efd ee efd ef d d Z Gd ddeZ dS))Union) ImageModule)Tensortensor) KORNIA_CHECKKORNIA_CHECK_IS_TENSORsrc1alphasrc2betagammareturncCst|t|t|j|jkd|jd|jt|tr(t|j|jkdn t||j|jd}t|tr@t|j|jkdn t||j|jd}t|trXt|j|jkdn t||j|jd}|||||S)aCalculate the weighted sum of two Tensors. .. image:: _static/img/add_weighted.png The function calculates the weighted sum of two Tensors as follows: .. math:: out = src1 * alpha + src2 * beta + gamma Args: src1: Tensor with an arbitrary shape, equal to shape of src2. alpha: weight of the src1 elements as Union[float, Tensor]. src2: Tensor with an arbitrary shape, equal to shape of src1. beta: weight of the src2 elements as Union[float, Tensor]. gamma: scalar added to each sum as Union[float, Tensor]. Returns: Weighted Tensor with shape equal to src1 and src2 shapes. Example: >>> input1 = torch.rand(1, 1, 5, 5) >>> input2 = torch.rand(1, 1, 5, 5) >>> output = add_weighted(input1, 0.5, input2, 0.5, 1.0) >>> output.shape torch.Size([1, 1, 5, 5]) Notes: Tensor alpha/beta/gamma have to be with shape broadcastable to src1 and src2 shapes. z)src1 and src2 have different shapes. Got z and z%alpha has a different shape than src.)dtypedevicez$beta has a different shape than src.z%gamma has a different shape than src.)rrshape isinstancerrrr)rr r r r rG/home/ubuntu/.local/lib/python3.10/site-packages/kornia/enhance/core.py add_weighteds!"   rcs`eZdZdZdeeefdeeefdeeefddffdd Zd ed edefd d ZZ S) AddWeightedaCalculate the weighted sum of two Tensors. The function calculates the weighted sum of two Tensors as follows: .. math:: out = src1 * alpha + src2 * beta + gamma Args: alpha: weight of the src1 elements as Union[float, Tensor]. beta: weight of the src2 elements as Union[float, Tensor]. gamma: scalar added to each sum as Union[float, Tensor]. Shape: - Input1: Tensor with an arbitrary shape, equal to shape of Input2. - Input2: Tensor with an arbitrary shape, equal to shape of Input1. - Output: Weighted tensor with shape equal to src1 and src2 shapes. Example: >>> input1 = torch.rand(1, 1, 5, 5) >>> input2 = torch.rand(1, 1, 5, 5) >>> output = AddWeighted(0.5, 0.5, 1.0)(input1, input2) >>> output.shape torch.Size([1, 1, 5, 5]) Notes: Tensor alpha/beta/gamma have to be with shape broadcastable to src1 and src2 shapes. r r r r Ncs t||_||_||_dSN)super__init__r r r )selfr r r  __class__rrrns  zAddWeighted.__init__rr cCst||j||j|jSr)rr r r )rrr rrrforwardtszAddWeighted.forward) __name__ __module__ __qualname____doc__rfloatrrr __classcell__rrrrrPs6rN) typingr kornia.corerModulerrkornia.core.checkrrr!rrrrrrs$      7