Image augmentation - noise added #381
Description
Relating directly to ML Ideas 12:
Goal to enhance robustness and generalisation of PVNet. To implement a set of specific image augmentation techniques, applied purely to the training data as a fundamental extra process stage.
Augmentation types to be considered such as small, random rotations - affine transformations. Additive Gaussian noise also certainly. Minimised rotations / stretching etc for NWP data.
Initial proposal to use the Albumentations library. Augmentations applied within the getitem method of the Dataset classes that handle satellite and NWP data - logic situated in the utils file itself.