Issue with visualisation being flipped

[azizalibasic]

Thank you for this contribution it has been very educational for me!

I am trying to train this model on a custom data set.

Can you confirm a few assumtions I have made?

1. This is the coordinate system:

   # COORDS:
   # Z: forward (roll)
   # Y: down (yaw)
   # X: right (pitch)
   #
   #
   # (forward) z
   #           \
   #            \
   #             *---------- x (right)
   #             |
   #             |
   #             |
   #             | Y (down)

2. For the sensors:

   1. roll is along z. +roll is clockwise
   2. yaw is along y. +yaw is clockwise
   3. pitch is along y. +pitch is down

Secondly, I have both my result & prediction for the segnet being flipped 180 deg. I am hoping you can give me any pointers on where to look.

Actual Values:

Expected Values:

[aharley]

I think you've got it right. In the BEV visualizations, things in front of the ego-car (with positive z) end up in the lower half of the image, because 0,0 is in the top-left corner, and X-1,Z-1 is in the bottom-right corner.

[azizalibasic]

Thanks for the verification @aharley !