Hi, thanks for the great paper and comprehensive code release. I had some questions about reproducing the CARLA results.
Are the correct hyper-parameters (to reproduce the paper results) in run_local_carla096.sh? For instance, I notice that encoder_stride=2 there, but the paper appendix appears to state it is 1.
I noticed that the README instructions utilize CARLA_0.9.8 (including adding the 0.9.8 Python API to the path, meaning we will use the carla_env.py for 0.9.8), but actually runs the CARLA_0.9.6 CarlaUE4.sh script. Is this correct?
I noticed in #8 that the ensemble model was necessary to perform well. Is that the case here too?
Hi, thanks for the great paper and comprehensive code release. I had some questions about reproducing the CARLA results.
run_local_carla096.sh
? For instance, I notice thatencoder_stride=2
there, but the paper appendix appears to state it is 1.carla_env.py
for 0.9.8), but actually runs the CARLA_0.9.6CarlaUE4.sh
script. Is this correct?ensemble
model was necessary to perform well. Is that the case here too?Thanks!