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

Hi, thanks for the great code!

I wonder do you have plans to support resuming from checkpoints for classification? As we all know, in terms of training ImageNet, the training process is really long and it can be interrupted somehow, but I haven't notice any code related to "resume" in scripts/classification/train_imagenet.py.

Maybe @hetong007 ? Thanks in advance.

Thank you for the great effort, you are putting into this project :) There is, however, a feature I miss; rotated bounding boxes. Especially when objects are thin and diagonal, an ordinary bounding box fits poorly. Examples of such cases are shown here: rotated bounding boxes

A way annotation could be

🐛 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()

with video_demo.py about 20% speed compared to your 1.0 repo. but thanks much for sharing!