Function sample_homography_np

script/utils/utils.py:125–239

Sample a random valid homography. Computes the homography transformation between a random patch in the original image and a warped projection with the same image size. As in `tf.contrib.image.transform`, it maps the output point (warped patch) to a transformed input point (original

(
        shape, shift=0, perspective=True, scaling=True, rotation=True, translation=True,
        n_scales=5, n_angles=25, scaling_amplitude=0.1, perspective_amplitude_x=0.1,
        perspective_amplitude_y=0.1, patch_ratio=0.5, max_angle=pi/2,
        allow_artifacts=False, translation_overflow=0.)

            save_image_saliancy(features[None,...].permute(1,0,2,3).cpu(), fn, normalize=True)

def sample_homography_np(
        shape, shift=0, perspective=True, scaling=True, rotation=True, translation=True,
        n_scales=5, n_angles=25, scaling_amplitude=0.1, perspective_amplitude_x=0.1,
        perspective_amplitude_y=0.1, patch_ratio=0.5, max_angle=pi/2,
        allow_artifacts=False, translation_overflow=0.):
    """Sample a random valid homography.

    Computes the homography transformation between a random patch in the original image
    and a warped projection with the same image size.
    As in `tf.contrib.image.transform`, it maps the output point (warped patch) to a
    transformed input point (original patch).
    The original patch, which is initialized with a simple half-size centered crop, is
    iteratively projected, scaled, rotated and translated.

    Arguments:
        shape: A rank-2 `Tensor` specifying the height and width of the original image.
        perspective: A boolean that enables the perspective and affine transformations.
        scaling: A boolean that enables the random scaling of the patch.
        rotation: A boolean that enables the random rotation of the patch.
        translation: A boolean that enables the random translation of the patch.
        n_scales: The number of tentative scales that are sampled when scaling.
        n_angles: The number of tentatives angles that are sampled when rotating.
        scaling_amplitude: Controls the amount of scale.
        perspective_amplitude_x: Controls the perspective effect in x direction.
        perspective_amplitude_y: Controls the perspective effect in y direction.
        patch_ratio: Controls the size of the patches used to create the homography. (like crop size)
        max_angle: Maximum angle used in rotations.
        allow_artifacts: A boolean that enables artifacts when applying the homography.
        translation_overflow: Amount of border artifacts caused by translation.

    Returns:
        A `Tensor` of shape `[1, 8]` corresponding to the flattened homography transform.
    """

    # print("debugging")


    # Corners of the output image
    pts1 = np.stack([[0., 0.], [0., 1.], [1., 1.], [1., 0.]], axis=0)
    # Corners of the input patch
    margin = (1 - patch_ratio) / 2
    pts2 = margin + np.array([[0, 0], [0, patch_ratio],
                                 [patch_ratio, patch_ratio], [patch_ratio, 0]])

    from numpy.random import normal
    from numpy.random import uniform
    from scipy.stats import truncnorm

    # Random perspective and affine perturbations
    # lower, upper = 0, 2
    std_trunc = 2
    # pdb.set_trace()
    if perspective:
        if not allow_artifacts:
            perspective_amplitude_x = min(perspective_amplitude_x, margin)
            perspective_amplitude_y = min(perspective_amplitude_y, margin)
        perspective_displacement = truncnorm(-1*std_trunc, std_trunc, loc=0, scale=perspective_amplitude_y/2).rvs(1)
        h_displacement_left = truncnorm(-1*std_trunc, std_trunc, loc=0, scale=perspective_amplitude_x/2).rvs(1)