Michael Kösel
Michael Kösel
@cbachhuber not including the demo project in the build links successfully. So the problem should stem from the demo project.
Thanks you for testing this. I just pushed a commit to see if `GLEW_LIBRARIES` is the only change needed. So I guess no need for a PR but thanks a...
Sure go ahead 👍 . I suggest rebasing against my master branch as I have removed the build folder. So it has to be created again in the CI.
Current work is done here: https://github.com/TheCodez/dynamic-occupancy-grid-map/tree/ros
Definitely, we need like 100 iterations to get a real estimate. A real benchmark is needed to see those small improvements. But at least currently we can see that it's...
@fmassa I agree option 2 would be the best to avoid problems in the future
@lonlonago I'm also getting those black lines using your code. Any idea on how this could be fixed?
@gaikwadrahul8 @pyu10055 sorry for the late response. The model is: https://github.com/FIGLAB/EyeMU/tree/master/flask2/static/models/tfjsmodel4. If I remember correctly, there was another model in that repo in a different format, which I allowed me...
The TTA `RandomFlip3D` is causing the issue. Additionally `test_mode=True` is also required in `LoadPointsFromMultiSweeps` for it to be deterministic. So for example update your test pipeline to the following: ```python...
Increasing the step value from 5 to 20 improves time a lot and only generates a slightly bigger atlas.