Mapping of old pixels to new using torchvision.transforms.functional.rotate

[Amrit_Das]

Its very simple you just have to create a rotation matrix :

how to rotate an image using rotation matrix.

or you can check this post for suggested codes:

Affine transformation matrix paramters conversion

How are you comparing the results? It seems scipy.ndimage.affine_transform uses pixel values for the translation part, while F.affine_grid seems to want values in the range [-1, 1] (which you already provided). This code tries to rotate and translate a line: x = torch.eye(10).view(1, 1, 10, 10) theta = torch.zeros(1, 2, 3) angle = np.pi/2. theta[:, :, :2] = torch.tensor([[np.cos(angle), -1.0*np.sin(angle)], [np.sin(angle), np.cos(angle)]]) theta[:, :, 2] = 0.5 …