Suppose there are two parallel universes that train deep learning models for color resolution.
The first universe uses grayscaled image as input that has dimension (640,480,1), the second universe uses RGB332 image as input that has same dimension as first universe which is (640,480,1).
Both same output which RGB888.
With same initializer, same moment, same architecture, same dataset, and same training stop epoch, but just different color format in dataset. Leaving no stochastic configuration initially.
So, which universe that has best model?
