bradyz/2020_CARLA_challenge

Error when running run_evaluation.sh

Closed this issue · 4 comments

Traceback (most recent call last):
File "/home/abdallahaymaan/2020_CARLA_challenge/leaderboard/leaderboard/leaderboard_evaluator.py", line 26, in
import carla
ModuleNotFoundError: No module named 'carla'

although the stated exports were done including the CARLA_ROOT

has anyone encountered such issue?
any help will be appreciated!

can you paste the full command you ran?

export PORT=2000
export DEBUG_CHALLENGE=0
export REPETITIONS=1
export ROUTES=/home/abdallahaymaan/2020_CARLA_challenge/leaderboard/data/routes_devtest.xml
export CHECKPOINT_ENDPOINT=tmp.txt
export SCENARIOS=/home/abdallahaymaan/2020_CARLA_challenge/leaderboard/data/all_towns_traffic_scenarios_public.json
export CARLA_ROOT=/home/abdallahaymaan/CARLA_0.9.9
conda activate carla.9
then inside the 2020_CARLA_challenge dir
./leaderboard/scripts/run_evaluation.sh

Also i edited the second line in run_evaluation.sh
from
python ${LEADERBOARD_ROOT}/leaderboard/leaderboard_evaluator.py
to
python /home/abdallahaymaan/2020_CARLA_challenge/leaderboard/leaderboard/leaderboard_evaluator.py \

OUTPUT:

Traceback (most recent call last):
File "/home/abdallahaymaan/2020_CARLA_challenge/leaderboard/leaderboard/leaderboard_evaluator.py", line 26, in
import carla
ModuleNotFoundError: No module named 'carla'

what I want to do is to visualize the results of the pretrained model (epoch=24.ckpt) through tables.
a route_19.txt was created containing data regarding the results of the run, is visualizing it possible?

sure thing, the route_19.txt should be in json

I recommend you run exactly the command in the README, not the run_evaluation.sh script directly.