feature visualization: add preprocess parameter to handle various input range

[fel-thomas]

Each model has its own input range, actually we only handle [0, 1] : the output of the sigmoid or clip.
We could investigate what solution should be adopted:

• rescale after the current procedure: x = x * (x_max - x_min) - x_min
• allow the user to pass a predefined function
• manipulate in [0, 255] then use the appropriate preprocess at the end