Question regarding Caltech V.S KITTI Preprocessing

[LeoXinhaoLee]

Hi, thanks so much for releasing code for this inspiring work!

I notice that in the get_sequence method of class KITTI() you normalize the image by (x / 127.5) - 1, which makes its value in range [-1.0, 1.0]. However, in class CALTECH, the normalization becomes (x / 255.0), which makes its value in range [0, 1.0] (here ignoring shade).

Could you please explain the reason for this difference to me? Thank you very much!