6a4fa82792bddc6126eaf944956f49f0a0cb7ca7,kornia/filters/sobel.py,Sobel,forward,#Sobel#Any#,152

Before Change

            "normalized=" + str(self.normalized) + ")"

    def forward(self, input: torch.Tensor) -> torch.Tensor:  // type: ignore
        if not torch.is_tensor(input):
            raise TypeError("Input type is not a torch.Tensor. Got {}"
                            .format(type(input)))
        if not len(input.shape) == 4:
            raise ValueError("Invalid input shape, we expect BxCxHxW. Got: {}"
                             .format(input.shape))
        // comput the x/y gradients
        edges: torch.Tensor = spatial_gradient(input,
                                               normalized=self.normalized)

        // unpack the edges
        gx: torch.Tensor = edges[:, :, 0]
        gy: torch.Tensor = edges[:, :, 1]

        // compute gradient maginitude
        magnitude: torch.Tensor = torch.sqrt(gx * gx + gy * gy + self.eps)
        return magnitude


// functiona api
// TODO: In terms of functional API, there should not be any initialization of an nn.Module.

After Change

            "normalized=" + str(self.normalized) + ")"

    def forward(self, input: torch.Tensor) -> torch.Tensor:
        return sobel(input, self.normalized, self.eps)

Instances