"clipped" transformations not documented as such

[vedal]

📚 Documentation

The behavior of clipping values to [0,1] after GaussNoise and some other similar functions should be documented under each transform. In the current state of the library, the only way to know if values are clipped or not is by digging into source.

A better alternative would be allowing the user to control clipping through a kwarg, or a parameter like Normalize().max_pixel_value for when image isn't yet normalized