How to use the torchgeometry.color.BgrToRgb function in torchgeometry

To help you get started, we’ve selected a few torchgeometry examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github kornia / kornia / test / test_color.py View on Github external
[[2., 2.],
                              [2., 2.]],

                             [[3., 3.],
                              [3., 3.]]])  # 3x2x2

        expected = torch.tensor([[[3., 3.],
                                  [3., 3.]],

                                 [[2., 2.],
                                  [2., 2.]],

                                 [[1., 1.],
                                  [1., 1.]]])  # 3x2x2

        f = color.BgrToRgb()
        assert_allclose(f(data), expected)
github kornia / kornia / test / test_color.py View on Github external
[[2., 2.],
                                   [2., 2.]],

                                  [[1., 1.],
                                   [1., 1.]]],

                                 [[[3., 3.],
                                   [3., 3.]],

                                  [[2., 2.],
                                   [2., 2.]],

                                  [[1., 1.],
                                   [1., 1.]]]])  # 2x3x2x2

        f = color.BgrToRgb()
        out = f(data)
        assert_allclose(out, expected)
github kornia / kornia / test / test_color.py View on Github external
def test_gradcheck(self):

        # prepare input data
        data = torch.tensor([[[1., 1.],
                              [1., 1.]],

                             [[2., 2.],
                              [2., 2.]],

                             [[3., 3.],
                              [3., 3.]]])  # 3x2x2

        data = utils.tensor_to_gradcheck_var(data)  # to var

        assert gradcheck(color.BgrToRgb(), (data,),
                         raise_exception=True)