Add Seam Carving transform for images, masks, bounding boxes, landmarks:

https://www.pyimagesearch.com/2017/01/23/seam-carving-with-opencv-python-and-scikit-image/

https://github.com/andrewdcampbell/seam-carving

Description

When the image array passed to skimage.segmentation.slic() is a float array containing NaNs, the routine frequently crashes (most of the time, in my case). In Spyder, this causes a silent failure, with the print statement below failing to execute and the environment being reset. I've observed this behavior under both Windows and Linux.

Way to reproduce

import nu

Link: https://kornia.readthedocs.io/en/latest/geometry.conversions.html#kornia.geometry.conversions.angle_axis_to_quaternion

Input and output are described as:
Input: (∗,3) where * means, any number of dimensions
Output: (∗,4)

While the example shows:

angle_axis = torch.rand(2, 4) # Nx4 quaternion = kornia.angle_axis_to_quaternion(angle_axis) # Nx3

The example indicates that in

🐛 Bug Report

If you try to run experiment in system/docker container where missing git (in system) your code will crush at this line:

https://github.com/catalyst-team/catalyst/blob/master/catalyst/utils/pipelines.py#L4

with message like this:

Traceback (most recent call last):
  File "/usr/local/lib/python3.7/site-packages/git/__init__.py", line 83, in <module>
    refresh()

Can you please add some performance numbers to the main project docs indicating inference latency running some common hardware options e.g. AWS p2, GCP gpu instance, CPU inference, Raspbery pi, etc.