autonomousvision / data_aggregation Goto Github PK

Thanks for your excellent work, I'd like to konw does it work for carla 0.9x?

when i run the comand :python3 multi_gpu_collection.py -ids 0 -n 1 -g 1 -e 10 -pt /data2/data_aggregation -ct carlagear -m expert
i meet the issue
pygame 1.9.4
Hello from the pygame community. https://www.pygame.org/contribute.html
using gpu id: 0
ERROR:root:(localhost:10000) connection closed
ERROR:root:(localhost:10000) connection closed

for a long time...

and i found the carlagear not run ,when i use "docker ps".

then i run carla in a docker singely ,use command :docker run -it --runtime=nvidia -e NVIDIA_VISIBLE_DEVICES=0 carlagear /bin/bash CarlaUE4.sh /Game/Maps/Town01 -windowed -world-port=10000 -benchmark -fps=10.

and printed the error:
[2020.09.17-18.03.28:033][ 0]LogInit: Error: FLinuxApplication::CreateLinuxApplication() : InitSDL() failed, cannot create application instance.

I use Xshell to log in a server do this work, and not have gui to display.
so How to solve this problem. thanks a lot.

miss init.py in dirve cause the problem. add the file from coiltraine solve it.

pygame 1.9.4
Hello from the pygame community. https://www.pygame.org/contribute.html
Traceback (most recent call last):
File "multi_gpu_collection.py", line 10, in
from collect import collect
File "/home/wangchangquan/data_aggregation/collect.py", line 29, in
from coil_core import validate_single_model
File "/home/wangchangquan/data_aggregation/coil_core/init.py", line 2, in
from .executer import execute_train, execute_validation, execute_drive, folder_execute
File "/home/wangchangquan/data_aggregation/coil_core/executer.py", line 11, in
from . import train, validate, run_drive
File "/home/wangchangquan/data_aggregation/coil_core/run_drive.py", line 19, in
from drive import CoILAgent
ImportError: cannot import name 'CoILAgent'

in function get_causes_of_end

    f = open(summary_file, "rU")
    header_summary = f.readline()

    header_summary = header_summary.split(',')
    header_summary[-1] = header_summary[-1][:-2]
    f.close()

-2 seems to be -1

• before index
  my head_summary content is
  end_pedestrian_collision,end_vehicle_collision,end_other_collision,weather,rep,start_point,initial_distance,final_distance,number_red_lights,exp_id,number_green_lights,final_time,result,end_point,time_out
• after index
  ['end_pedestrian_collision', 'end_vehicle_collision', 'end_other_collision', 'weather', 'rep', 'start_point', 'initial_distance', 'final_distance', 'number_red_lights', 'exp_id', 'number_green_lights', 'final_time', 'result', 'end_point', 'time_ou']