Implement additional data augmentations for training

In https://github.com/mapbox/robosat/pull/19 we implemented data augmentations like random rotations and random flipping. In the context of aerial and satellite imagery we should implement additional augmentations:

• Implement random scaling (image with bicubic, mask with nearest).
• Implement random color jitter in HSV color space (image only).
• Implement motion blur (directional, not just gaussian blur). Mostly for drone imagery use-case.
• Implement stitching artifacts. Simulate with shear (offset of part of the image) and blur on only one side.
• Implement changes in contrast.

Note: implement contrast jitter as something like add -0.2..0.2 and gamma (x**n) 0.8..1.2 to the luminance channel. That’s important because the camera is doing auto-exposure and you can get very different contrast profiles for under cloud v. under sun, the same feature in and out of a tree’s shadow, etc.

Start by reading pull request #19, which introduced the existing rotation and flipping augmentations, and trace how those augmentations are applied during training. Implement and validate the listed scaling, color, blur, stitching, contrast, and gamma behaviors, preserving the specified image-versus-mask interpolation and image-only rules; done means all checklist items are covered.