augmentation: control degradation rate

[bertsky]

IIUC, in the current implementation, the rate between original images and augmented variants will be a fixed 1 : N for N kinds of augmentation that have been enabled:

sbb_pixelwise_segmentation/utils.py

Line 92 in 63fcb96

random.shuffle(n)

This makes it hard to control what kind of degradation to learn how fast. IMHO the precomputed files should be somehow indexed in such a way that the randomized generator can mix in augmented images (of any kind) at a well-defined rate. You would then be able to configure, say, rotation at p = 0.2. Think imgaug!

Also, I believe it should at least be possible to increase that rate throughout the training procedure.