I just started using this after initial setup done right I am able to see agent output and NPc's but the trainer is always in waiting state

At first,I downloaded this zip and uncompressed it into the folder D:\carla\PythonAPI\examples,when running the train.py,the result error:
Traceback (most recent call last): File "train.py", line 9, in <module> from sources import start_carla, restart_carla File "D:\carla\PythonAPI\examples\sources\__init__.py", line 2, in <module> from .carla import CarlaEnv, carla as carla_simulator, get_exec_command as get_carla_exec_command, kill_processes as kill_carla_processes, start as start_carla, restart as restart_carla, ACTIONS, ACTIONS_NAMES, CarlaEnvSettings, CARLA_SETTINGS_STATE, CARLA_SETTINGS_STATE_MESSAGE File "D:\carla\PythonAPI\examples\sources\carla.py", line 10, in <module> import carla ModuleNotFoundError: No module named 'carla'
How to run these programs?
Preciate your kind reply.

VScode is highlighting many errors in carla.py in every carla. line and I think it's because of this line:
self.client = carla.Client(*settings.CARLA_HOSTS[carla_instance][:2])
In all the other files Carla API is working well, also "CARLA_HOSTS" is set right in settings.py so that doesn't seem to be the problem.
The script runs and the simulator opens but it keeps printing "ERROR" on "Carla1" and in "Agent1" and nothing happens, nor npc's spawn, neither agent. @daniel-kukiela @Sentdex

Is there a way to modify the files to let the agents run at a fixed timestep, or in synchronous mode?

I have tried the usual:

        self.frame = self.world.apply_settings(carla.WorldSettings(no_rendering_mode=False,synchronous_mode=True,fixed_delta_seconds=self.delta_seconds))
        self.clock = pygame.time.Clock()

with no success.

When I run the code train.py, the following error code is displayed:

the nvidia-smi results are:

My tensorflow version: 1.15.0. Carla version: 0.9.11

While running the reinforced learning code for carla the hparams file was not found and and error was displayed:

Traceback (most recent call last): File "/home/carlauser/Carla-RL/play.py", line 18, in <module> for model in hparams['models']: TypeError: 'NoneType' object is not subscriptable

Any help?

the code seems like starting with printing the following:
Starting...
Waiting for Carla...
Calculating weights size...
Starting trainer...
Starting agents...
Ready

it also print some empty stats then it throws this error
terminate called after throwing an instance of 'std::runtime_error'
what(): trying to operate on a destroyed actor; an actor's function was called, but the actor is already destroyed.
Aborted (core dumped)

can anyone help with a possible solution please?
I am using cuda version 10.0
cudnn = 7.4.2
Tensorflow-gpu = 1.14
Gpu nvidia GeForce GTX 1050
Thanks in advance

When I run any of the scripts, nothing happens. There are no errors or warnings

whenever i run all the files i face "No module named 'settings'" this issue, how to solve it ?

can you tell us clearly how to run this repository

hello,
after training the Xception model over 1000 episode. the restarting episode always come after 2 step, the agent is not moving properly.
is the problem of my PC low performance.

Hi,

System specifications:
OS: Ubuntu 18.04,
Memory: 15.7 GiB,
Processor: AMD® Ryzen 7 3800x 8-core processor × 16,
GPU 4 GiB.
Python Version - 3.5
CARLA Version - 0.9.5

Please find the attached Test_1.py, I am attempting to run, while doing so, I am encountering syntax error - File "Test_1.py", line 311 agent.model.save(f'models/{MODEL_NAME}{max_reward:>7.2f}max{average_reward:>7.2f}avg{min_reward:_>7.2f}min{int(time.time())}.model') (Screenshot Attached).

I couldn't figure out the reason for the sytax error - I even tried to add -- agent.model.save('{}'.format(models/(MODEL_NAME)(max_reward:>7.2f)max(average_reward:>7.2f)avg(min_reward:_>7.2f)min(int(time.time())).model)), Still I encountered the same error.

CARLA_Test_1_PY.pdf

Can you please help me resolve this problem.

Thanks
Guru

Even after over 5000 Episodes the Training doesn't start.
The following error messages keep popping up:

X Error: BadShmSeg (invalid shared segment parameter) 128
  Extension:    130 (MIT-SHM)
  Minor opcode: 3 (X_ShmPutImage)
  Resource id:  0x2c0000e

I'm running the training inside a docker container using the following command:

docker run -it --gpus all -v /tmp/.X11-unix:/tmp/.X11-unix \
 -v ~/.Xauthority:/home/root/.Xauthority \
--link carla_server \
-u 1000 \
--env DISPLAY=:0 sentdex_carla_rl_image bash -c '
echo started & \
socat TCP-LISTEN:2000,fork TCP:carla_server:2000 & \
socat TCP-LISTEN:2001,fork TCP:carla_server:2001 & \
sleep 1 && \
#./carla_095/PythonAPI/examples/manual_control.py && \
python3 train.py
'

When I start train.py a got message
Starting...
Starting Carla...
and nothing happend. The agent does not appear on the map

when i run play.py or any other scripts, nothing happens, no error or any kind of output.
i have installed all the dependencies and the server is running without issue. ?

run train.py,The agent keeps spinning, how to solve?

I'm learning the program from https://pythonprogramming.net/control-camera-sensor-self-driving-autonomous-cars-carla-python/ and run the code in this website on ubuntu 18.04，python 3.6 and carla 0.9.9, but I cannot get continuous images through the following code:
def process_img(image): i = np.array(image.raw_data) i2 = i.reshape((IM_HEIGHT, IM_WIDTH, 4)) i3 = i2[:, :, :3] cv2.imshow("", i3) cv2.waitKey(1) return i3/255.0
The image is freezing in the first frame which is strange, I really don't know what's going wrong with it and sincerely hoping for any help. Thank you very much!

I tried tensorflow 1.13.1 and keras 2.2.4 as suggested in other issues. But i only print out
Starting...
Starting Carla...
and no sight of the agent or whether the training has started? Can anyone help me out?

How to solve this problem?

TensorFlow 1.13.1 Keras 2.2.4
CUDA 10.0.130
cudnn 7.4
I ran train.py in the environment, but it falls into an infinite loop. I do not know the reason.

hello as mentioned in the titlle i want to spawn a vehicle in front of the ego vehicle, i want to know which file should i change and if have an idea what to change exactly
Thanks

Hi all,

Atlhough I have set the save chekpoint flag at every 100 episodes my models folder seems to be empty. Do you know why this might be the case?

I ran the code with just python train.py and although I do see the training stats I can't find the model anywhere

Best,

Filip

would you please upload pre-train weights?

so when i run train.py carla simulator starts and then in the terminal it says starting carla and then i get the error:

streaming client: connection failed: No connection could be made because the target machine actively refused it
INFO: streaming client: connection failed: No connection could be made because the target machine actively refused it