gnosisyuw / CrevNet-Traffic4cast

Apache License 2.0
27 stars 6 forks source link

Question regarding Caltech V.S KITTI Preprocessing #16

Open LeoXinhaoLee opened 1 year ago

LeoXinhaoLee commented 1 year ago

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!