Kornia.geometry ¶ geometric image transformations is another key ingredient in computer vision to manipulate images Since geometry operations are typically performed in 2d or 3d, we provide several algorithms to work with both cases. Kornia.augmentation ¶ this module implements in a high level logic The main features of this module, and similar to the rest of the library, is that can it perform data augmentation routines in a batch mode, using any supported device, and can be used for backpropagation. Kornia.feature.hessian_response(input, grads_mode='sobel', sigmas=none) ¶ compute the absolute of determinant of the hessian matrix Function does not do any normalization or nms
The response map is computed according the following formulation: Kornia.filters ¶ the functions in this sections perform various image filtering operations Blurring ¶ kornia.filters.bilateral_blur(input, kernel_size, sigma_color, sigma_space, border_type='reflect', color_distance_type='l1') ¶ blur a tensor using a bilateral filter Installation ¶ to install kornia, you can do it in two different ways Using the provided pypi wheels or directly from source. Kornia is a differentiable library that allows classical computer vision to be integrated into deep learning models
Kornia.geometry.transform.warp_points_tps(points_src, kernel_centers, kernel_weights, affine_weights) ¶ warp a tensor of coordinate points using the thin plate spline defined by arguments. Kornia.color.rgba_to_rgb(image, background_color=none) ¶ convert an image from rgba to rgb using alpha compositing The function composites the input rgba image over a background color If no background color is provided, it defaults to a white background
OPEN
