search

Luca96 / carla-driving-rl-agent

Code for the paper "Reinforced Curriculum Learning for Autonomous Driving in CARLA" (ICIP 2021)
MIT License
108 stars 25 forks source link

Error related to keras #30

Open SExpert12 opened 5 months ago

SExpert12 commented 5 months ago

Hi, I am getting this error. I tried to change as suggested in this but still I am not able to run the file.

pygame 2.0.1 (SDL 2.0.14, Python 3.8.10) Hello from the pygame community. https://www.pygame.org/contribute.html /home/.local/lib/python3.8/site-packages/pandas/core/computation/expressions.py:20: UserWarning: Pandas requires version '2.7.3' or newer of 'numexpr' (version '2.7.1' currently installed). from pandas.core.computation.check import NUMEXPR_INSTALLED WARNING:tensorflow:From main.py:9: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version. Instructions for updating: Use tf.config.list_physical_devices('GPU') instead. 2024-06-26 03:13:12.082157: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA 2024-06-26 03:13:12.104117: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 3593325000 Hz 2024-06-26 03:13:12.105007: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7fe1cc000b60 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2024-06-26 03:13:12.105049: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2024-06-26 03:13:12.107924: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcuda.so.1 2024-06-26 03:13:12.134793: E tensorflow/stream_executor/cuda/cuda_driver.cc:313] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected 2024-06-26 03:13:12.134833: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: 2024-06-26 03:13:12.134841: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: zenten 2024-06-26 03:13:12.134935: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:200] libcuda reported version is: 535.171.4 2024-06-26 03:13:12.134959: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:204] kernel reported version is: 535.171.4 2024-06-26 03:13:12.134966: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:310] kernel version seems to match DSO: 535.171.4 Traceback (most recent call last): File "main.py", line 11, in from core import learning File "/home/carla-driving-rl-agent-master/core/init.py", line 2, in from core.carla_agent import CARLAgent, FakeCARLAEnvironment File "/home/carla-driving-rl-agent-master/core/carla_agent.py", line 8, in import rl File "/home/carla-driving-rl-agent-master/rl/init.py", line 1, in import rl.augmentations File "/home/carla-driving-rl-agent-master/rl/augmentations/init.py", line 2, in from rl.augmentations.augmentations import * File "/home/carla-driving-rl-agent-master/rl/augmentations/augmentations.py", line 7, in from rl import utils File "/home/carla-driving-rl-agent-master/rl/utils.py", line 16, in from tensorflow.keras.optimizers.schedules import LearningRateSchedule File "/home/.local/lib/python3.8/site-packages/tensorflow/keras/init.py", line 19, in from . import datasets File "/home/.local/lib/python3.8/site-packages/tensorflow/keras/datasets/init.py", line 14, in from . import imdb File "/home/.local/lib/python3.8/site-packages/tensorflow/keras/datasets/imdb/init.py", line 11, in from tensorflow.python.keras.datasets.imdb import get_word_index File "/home/.local/lib/python3.8/site-packages/tensorflow/python/keras/datasets/imdb.py", line 25, in from tensorflow.python.keras.preprocessing.sequence import _remove_long_seq File "/home/.local/lib/python3.8/site-packages/tensorflow/python/keras/preprocessing/init.py", line 26, in from tensorflow.python.keras.preprocessing import image File "/home/.local/lib/python3.8/site-packages/tensorflow/python/keras/preprocessing/image.py", line 23, in from keras_preprocessing import image File "/home/.local/lib/python3.8/site-packages/keras_preprocessing/image.py", line 20, in backend = get_keras_submodule('backend') File "/home/.local/lib/python3.8/site-packages/keras_preprocessing/init.py", line 24, in get_keras_submodule raise ImportError('You need to first import keras ' ImportError: You need to first import keras in order to use keras_preprocessing. For instance, you can do:

import keras
from keras_preprocessing import image

Or, preferably, this equivalent formulation:


from keras import preprocessing
Luca96 commented 5 months ago

There are multiple errros. First, there is a mismatch in pandas version, then it seems that CUDA in not properly installed, and lastly, keras failing for some reason...

Could you list the packages along their version you have installed (I presume) in a virtualenv?

SExpert12 commented 5 months ago

Hi, Thanks for your reply. This is the list of packages: Package Version

absl-py 2.1.0 astunparse 1.6.3 cachetools 5.3.3 carla 0.9.15 certifi 2024.6.2 charset-normalizer 3.3.2 cloudpickle 3.0.0 cycler 0.12.1 decorator 5.1.1 dm-tree 0.1.8 fonttools 4.53.0 gast 0.3.3 google-auth 2.30.0 google-auth-oauthlib 1.0.0 google-pasta 0.2.0 grpcio 1.64.1 gym 0.26.2 gym-notices 0.0.8 h5py 2.10.0 idna 3.7 importlib_metadata 8.0.0 Keras-Preprocessing 1.1.2 kiwisolver 1.4.5 Markdown 3.6 MarkupSafe 2.1.5 matplotlib 3.5.3 networkx 3.1 numpy 1.18.5 oauthlib 3.2.2 opencv-python 4.10.0.84 opt-einsum 3.3.0 packaging 24.1 pillow 10.3.0 pip 24.1 protobuf 3.20.0 pyasn1 0.6.0 pyasn1_modules 0.4.0 pygame 2.6.0 pyparsing 3.1.2 python-dateutil 2.9.0.post0 requests 2.32.3 requests-oauthlib 2.0.0 rsa 4.9 scipy 1.9.3 setuptools 70.1.0 six 1.16.0 tensorboard 2.14.0 tensorboard-data-server 0.7.2 tensorflow 2.3.1 tensorflow-estimator 2.3.0 tensorflow-probability 0.11.1 termcolor 2.4.0 urllib3 2.2.2 Werkzeug 3.0.3 wheel 0.43.0 wrapt 1.16.0 zipp 3.19.2

Now I am getting this error. Hello from the pygame community. https://www.pygame.org/contribute.html 2024-06-27 02:24:12.741430: W tensorflow/stream_executor/platform/default/dso_loader.cc:59] Could not load dynamic library 'libcudart.so.10.1'; dlerror: libcudart.so.10.1: cannot open shared object file: No such file or directory 2024-06-27 02:24:12.741458: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. WARNING:tensorflow:From main.py:36: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version. Instructions for updating: Use tf.config.list_physical_devices('GPU') instead. 2024-06-27 02:24:13.392218: I tensorflow/core/platform/cpu_feature_guard.cc:142] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN)to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-06-27 02:24:13.421715: I tensorflow/core/platform/profile_utils/cpu_utils.cc:104] CPU Frequency: 3593325000 Hz 2024-06-27 02:24:13.422517: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x321a060 initialized for platform Host (this does not guarantee that XLA will be used). Devices: 2024-06-27 02:24:13.422540: I tensorflow/compiler/xla/service/service.cc:176] StreamExecutor device (0): Host, Default Version 2024-06-27 02:24:13.425373: I tensorflow/stream_executor/platform/default/dso_loader.cc:48] Successfully opened dynamic library libcuda.so.1 2024-06-27 02:24:13.453204: E tensorflow/stream_executor/cuda/cuda_driver.cc:314] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected 2024-06-27 02:24:13.453237: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: ryzen 2024-06-27 02:24:13.453243: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: ryzen 2024-06-27 02:24:13.453309: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:200] libcuda reported version is: 535.171.4 2024-06-27 02:24:13.453326: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:204] kernel reported version is: 535.171.4 2024-06-27 02:24:13.453330: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:310] kernel version seems to match DSO: 535.171.4 /home/rlagent/lib/python3.8/site-packages/gym/spaces/box.py:127: UserWarning: WARN: Box bound precision lowered by casting to float32 logger.warn(f"Box bound precision lowered by casting to {self.dtype}") WARNING: Version mismatch detected: You are trying to connect to a simulator that might be incompatible with this API WARNING: Client API version = 0.9.15 WARNING: Simulator API version = 0.9.14-6-g43b5e7064-dirty WARNING: Version mismatch detected: You are trying to connect to a simulator that might be incompatible with this API WARNING: Client API version = 0.9.15 WARNING: Simulator API version = 0.9.14-6-g43b5e7064-dirty Weather changed to WeatherParameters(cloudiness=5.000000, precipitation=0.000000, precipitation_deposits=0.000000, wind_intensity=10.000000, sun_azimuth_angle=-1.000000, sun_altitude_angle=45.000000, fog_density=2.000000, fog_distance=0.750000, fog_falloff=0.100000, wetness=0.000000, scattering_intensity=1.000000, mie_scattering_scale=0.030000, rayleigh_scattering_scale=0.033100, dust_storm=0.000000). Traceback (most recent call last): File "main.py", line 81, in stage1.run2(epochs=100, epoch_offset=0) File "/home/rlagent/core/learning.py", line 146, in run2 self.init() File "/home/rlagent/core/learning.py", line 117, in init self.agent = self.agent_class(self.env, self.agent_args) File "/home/rlagent/core/carla_agent.py", line 97, in init super().init(*args, name=name, network=network_spec, clip_norm=clip_norm, *kwargs) File "/home/rlagent/rl/agents/ppo.py", line 36, in init super().init(args, name=name, kwargs) File "/home/rlagent/rl/agents/agents.py", line 28, in init self.set_random_seed(seed) File "/home/rlagent/rl/agents/agents.py", line 70, in set_random_seed self.env.seed(seed) AttributeError: 'CARLAEnv' object has no attribute 'seed'

Thanks once again for your reply.

Luca96 commented 5 months ago

@SExpert12 I think you need to downgrade gym to version 0.20.1 or 0.19.6. I don't remember the exact version so the last number may be wrong, so please double-check. Also let me know which version of gym works for you so that I'll update the requirements file

SExpert12 commented 5 months ago

Sure. Thanks for quick reply. Let me check and get back to you.

Thanks once again for your help.

SExpert12 commented 5 months ago

Hi, I got error related to numpy and tensorflow. So I installed the latest tensorflow. I am sharing package details.

Package Version

absl-py 2.1.0 astunparse 1.6.3 cachetools 5.3.3 carla 0.9.15 certifi 2024.6.2 charset-normalizer 3.3.2 cloudpickle 1.6.0 contourpy 1.1.1 cycler 0.12.1 decorator 5.1.1 dm-tree 0.1.8 flatbuffers 24.3.25 fonttools 4.53.0 gast 0.3.3 google-auth 2.30.0 google-auth-oauthlib 0.4.6 google-pasta 0.2.0 grpcio 1.64.1 gym 0.19.0 h5py 2.10.0 idna 3.7 importlib-metadata 8.0.0 importlib-resources 6.4.0 keras 2.8.0 Keras-Preprocessing 1.1.2 kiwisolver 1.4.5 libclang 18.1.1 Markdown 3.6 MarkupSafe 2.1.5 matplotlib 3.7.5 networkx 3.1 numpy 1.20.0 oauthlib 3.2.2 opencv-python 4.10.0.84 opt-einsum 3.3.0 packaging 24.1 pillow 10.3.0 pip 21.0 protobuf 3.20.0 pyasn1 0.6.0 pyasn1-modules 0.4.0 pygame 2.6.0 pyparsing 3.1.2 python-dateutil 2.9.0.post0 requests 2.32.3 requests-oauthlib 2.0.0 rsa 4.9 scipy 1.10.1 setuptools 65.5.0 six 1.16.0 tensorboard 2.8.0 tensorboard-data-server 0.6.1 tensorboard-plugin-wit 1.8.1 tensorflow 2.8.0 tensorflow-estimator 2.3.0 tensorflow-io-gcs-filesystem 0.34.0 tensorflow-probability 0.11.1 termcolor 2.4.0 tf-estimator-nightly 2.8.0.dev2021122109 typing-extensions 4.12.2 urllib3 2.2.2 werkzeug 3.0.3 wheel 0.38.0 wrapt 1.16.0 zipp 3.19.2

The program is started to run but I am getting error related to spawn point. It is chosen randomly and I don't understand how to change.

pygame 2.6.0 (SDL 2.28.4, Python 3.8.10) Hello from the pygame community. https://www.pygame.org/contribute.html 2024-06-27 07:37:20.235303: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory 2024-06-27 07:37:20.235335: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. WARNING:tensorflow:From main.py:36: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version. Instructions for updating: Use tf.config.list_physical_devices('GPU') instead. 2024-06-27 07:37:21.297341: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-06-27 07:37:21.325344: E tensorflow/stream_executor/cuda/cuda_driver.cc:271] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected 2024-06-27 07:37:21.325401: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: ryzen 2024-06-27 07:37:21.325410: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: ryzen 2024-06-27 07:37:21.325602: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:200] libcuda reported version is: 535.171.4 2024-06-27 07:37:21.325639: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:204] kernel reported version is: 535.171.4 2024-06-27 07:37:21.325647: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:310] kernel version seems to match DSO: 535.171.4 /home/ryzen/rlagent/rlagent/lib/python3.8/site-packages/gym/logger.py:34: UserWarning: WARN: Box bound precision lowered by casting to float32 warnings.warn(colorize("%s: %s" % ("WARN", msg % args), "yellow")) WARNING: Version mismatch detected: You are trying to connect to a simulator that might be incompatible with this API WARNING: Client API version = 0.9.15 WARNING: Simulator API version = 0.9.14-6-g43b5e7064-dirty WARNING: Version mismatch detected: You are trying to connect to a simulator that might be incompatible with this API WARNING: Client API version = 0.9.15 WARNING: Simulator API version = 0.9.14-6-g43b5e7064-dirty Weather changed to WeatherParameters(cloudiness=5.000000, precipitation=0.000000, precipitation_deposits=0.000000, wind_intensity=10.000000, sun_azimuth_angle=-1.000000, sun_altitude_angle=45.000000, fog_density=2.000000, fog_distance=0.750000, fog_falloff=0.100000, wetness=0.000000, scattering_intensity=1.000000, mie_scattering_scale=0.030000, rayleigh_scattering_scale=0.033100, dust_storm=0.000000). Random seed 51 set. Random seed 695516342 set. state_spec: {'state_image': (90, 360, 3), 'state_navigation': (5,), 'state_road': (9,), 'state_vehicle': (4,)} action_shape: 2 distribution: beta 2024-06-27 07:37:25.600724: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them. Optimizer: adam. Optimizer: adam. Optimizer: adam. Random seed 2362446593 set. env.reset No recommended values for 'speed' attribute Traceback (most recent call last): File "main.py", line 81, in stage1.run2(epochs=100, epoch_offset=0) File "/home/rlagent/core/learning.py", line 154, in run2 self.reinforcement_learning() File "/home/rlagent/core/learning.py", line 184, in reinforcement_learning self.agent.learn(**self.learn_args['agent']) File "/home/rlagent/rl/agents/ppo.py", line 492, in learn state = self.env.reset() File "/home/rlagent/core/carla_env.py", line 212, in reset return super().reset() File "/home/rlagent/rl/environments/carla/environment.py", line 940, in reset observation = super().reset() File "/home/rlagent/rl/environments/carla/environment.py", line 228, in reset self.reset_world() File "/home/rlagent/core/carla_env.py", line 221, in reset_world super().reset_world() File "/home/rlagent/rl/environments/carla/environment.py", line 517, in reset_world self.vehicle: carla.Vehicle = env_utils.spawn_actor(self.world, blueprint, self.origin) File "/home/rlagent/rl/environments/carla/env_utils.py", line 218, in spawn_actor raise ValueError(f'Cannot spawn actor. Try changing the spawn_point ({spawn_point.location}) to something else.') ValueError: Cannot spawn actor. Try changing the spawn_point (Location(x=-9.441488, y=91.994293, z=0.275307)) to something else.

Please help me resolve this issue also. Thanks

SExpert12 commented 5 months ago

Hi, I tried multiple towns. I run the CARLA server first and then I run the main.py. I got this error.

pygame 2.6.0 (SDL 2.28.4, Python 3.8.10) Hello from the pygame community. https://www.pygame.org/contribute.html 2024-06-27 07:49:39.607306: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory 2024-06-27 07:49:39.607340: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. WARNING:tensorflow:From main.py:36: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version. Instructions for updating: Use tf.config.list_physical_devices('GPU') instead. 2024-06-27 07:49:40.837347: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-06-27 07:49:40.867943: E tensorflow/stream_executor/cuda/cuda_driver.cc:271] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected 2024-06-27 07:49:40.867984: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: ryzen 2024-06-27 07:49:40.867993: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: ryzen 2024-06-27 07:49:40.868090: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:200] libcuda reported version is: 535.171.4 2024-06-27 07:49:40.868116: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:204] kernel reported version is: 535.171.4 2024-06-27 07:49:40.868122: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:310] kernel version seems to match DSO: 535.171.4 /home/ryzen/rlagent/rlagent/lib/python3.8/site-packages/gym/logger.py:34: UserWarning: WARN: Box bound precision lowered by casting to float32 warnings.warn(colorize("%s: %s" % ("WARN", msg % args), "yellow")) WARNING: Version mismatch detected: You are trying to connect to a simulator that might be incompatible with this API WARNING: Client API version = 0.9.15 WARNING: Simulator API version = 0.9.14-6-g43b5e7064-dirty WARNING: Version mismatch detected: You are trying to connect to a simulator that might be incompatible with this API WARNING: Client API version = 0.9.15 WARNING: Simulator API version = 0.9.14-6-g43b5e7064-dirty Weather changed to WeatherParameters(cloudiness=5.000000, precipitation=0.000000, precipitation_deposits=0.000000, wind_intensity=10.000000, sun_azimuth_angle=-1.000000, sun_altitude_angle=45.000000, fog_density=2.000000, fog_distance=0.750000, fog_falloff=0.100000, wetness=0.000000, scattering_intensity=1.000000, mie_scattering_scale=0.030000, rayleigh_scattering_scale=0.033100, dust_storm=0.000000). Random seed 51 set. Random seed 695516342 set. state_spec: {'state_image': (90, 360, 3), 'state_navigation': (5,), 'state_road': (9,), 'state_vehicle': (4,)} action_shape: 2 distribution: beta 2024-06-27 07:49:46.662932: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them. Optimizer: adam. Optimizer: adam. Optimizer: adam. Random seed 2362446593 set. env.reset No recommended values for 'speed' attribute Event CARLAEvent.RESET triggered. Sensor sensor.other.collision is already been started! Sensor sensor.other.imu is already been started! Sensor sensor.camera.rgb is already been started! Sensor sensor.camera.rgb is already been started! Sensor sensor.camera.rgb is already been started! Traceback (most recent call last): File "main.py", line 81, in stage1.run2(epochs=100, epoch_offset=0) File "/home/rlagent/core/learning.py", line 154, in run2 self.reinforcement_learning() File "/home/rlagent/core/learning.py", line 184, in reinforcement_learning self.agent.learn(**self.learn_args['agent']) File "/home/rlagent/rl/agents/ppo.py", line 492, in learn state = self.env.reset() File "/home/rlagent/core/carla_env.py", line 212, in reset return super().reset() File "/home/rlagent/rl/environments/carla/environment.py", line 940, in reset observation = super().reset() File "/home/rlagent/rl/environments/carla/environment.py", line 235, in reset self.skip(num_frames=self.num_frames_to_skip) File "/home/rlagent/rl/environments/carla/environment.py", line 412, in skip self.synchronous_context.tick(timeout=self.timeout) File "/home/rlagent/rl/environments/carla/tools/synchronous_mode.py", line 60, in tick data[name] = self._get_sensor_data(q, timeout) File "/home/rlagent/rl/environments/carla/tools/synchronous_mode.py", line 83, in _get_sensor_data data = sensor_queue.get(timeout=timeout) File "/usr/lib/python3.8/queue.py", line 178, in get raise Empty _queue.Empty

and then I run client again without refreshing server then I got the spawning error.

Luca96 commented 4 months ago

@SExpert12 Hello, and sorry for the late response. So, sometimes the CARLA simulator behaves a bit buggy so you need to close it and restart, again. This is because it can happen that the previously spawned vehicle is somehow not being destroyed: if so the episode will end prematurely, say on timestep 1.

SExpert12 commented 4 months ago

Hi,
I am again getting this same error. I created new venv and started from the beginning.

Hello from the pygame community. https://www.pygame.org/contribute.html 2024-07-04 11:11:52.131612: W tensorflow/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory 2024-07-04 11:11:52.131641: I tensorflow/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine. WARNING:tensorflow:From main.py:36: is_gpu_available (from tensorflow.python.framework.test_util) is deprecated and will be removed in a future version. Instructions for updating: Use tf.config.list_physical_devices('GPU') instead. 2024-07-04 11:11:53.140409: I tensorflow/core/platform/cpu_feature_guard.cc:151] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX2 FMA To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2024-07-04 11:11:53.173150: E tensorflow/stream_executor/cuda/cuda_driver.cc:271] failed call to cuInit: CUDA_ERROR_NO_DEVICE: no CUDA-capable device is detected 2024-07-04 11:11:53.173197: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:169] retrieving CUDA diagnostic information for host: ryzen 2024-07-04 11:11:53.173209: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:176] hostname: ryzen 2024-07-04 11:11:53.173315: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:200] libcuda reported version is: 535.183.1 2024-07-04 11:11:53.173349: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:204] kernel reported version is: 535.183.1 2024-07-04 11:11:53.173360: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:310] kernel version seems to match DSO: 535.183.1 /home/ryzen/rlagent/lucaagent/lib/python3.8/site-packages/gym/logger.py:34: UserWarning: WARN: Box bound precision lowered by casting to float32 warnings.warn(colorize("%s: %s" % ("WARN", msg % args), "yellow")) WARNING: Version mismatch detected: You are trying to connect to a simulator that might be incompatible with this API WARNING: Client API version = 0.9.14 WARNING: Simulator API version = 0.9.14-6-g43b5e7064-dirty WARNING: Version mismatch detected: You are trying to connect to a simulator that might be incompatible with this API WARNING: Client API version = 0.9.14 WARNING: Simulator API version = 0.9.14-6-g43b5e7064-dirty Weather changed to WeatherParameters(cloudiness=5.000000, cloudiness=5.000000, precipitation=0.000000, precipitation_deposits=0.000000, wind_intensity=10.000000, sun_azimuth_angle=-1.000000, sun_altitude_angle=45.000000, fog_density=2.000000, fog_distance=0.750000, fog_falloff=0.100000, wetness=0.000000, scattering_intensity=1.000000, mie_scattering_scale=0.030000, rayleigh_scattering_scale=0.033100, dust_storm=0.000000). sees 2338741697 Random seed 2338741697 set. state_spec: {'state_image': (90, 360, 3), 'state_navigation': (5,), 'state_road': (9,), 'state_vehicle': (4,)} action_shape: 2 distribution: beta 2024-07-04 11:11:57.492185: W tensorflow/python/util/util.cc:368] Sets are not currently considered sequences, but this may change in the future, so consider avoiding using them. Optimizer: adam. Optimizer: adam. Optimizer: adam. sees 3235473884 Random seed 3235473884 set. env.reset No recommended values for 'speed' attribute Event CARLAEvent.RESET triggered. Sensor sensor.other.collision is already been started! Sensor sensor.other.imu is already been started! Sensor sensor.camera.rgb is already been started! Sensor sensor.camera.rgb is already been started! Sensor sensor.camera.rgb is already been started! Traceback (most recent call last): File "main.py", line 81, in stage1.run2(epochs=100, epoch_offset=0) File "/home/rlagent/core/learning.py", line 154, in run2 self.reinforcement_learning() File "/home/rlagent/core/learning.py", line 184, in reinforcement_learning self.agent.learn(**self.learn_args['agent']) File "/home/rlagent/rl/agents/ppo.py", line 492, in learn state = self.env.reset() File "/home/rlagent/core/carla_env.py", line 212, in reset return super().reset() File "/home/rlagent/rl/environments/carla/environment.py", line 940, in reset observation = super().reset() File "/home/rlagent/rl/environments/carla/environment.py", line 235, in reset self.skip(num_frames=self.num_frames_to_skip) File "/home/rlagent/rl/environments/carla/environment.py", line 412, in skip self.synchronous_context.tick(timeout=self.timeout) File "/home/rlagent/rl/environments/carla/tools/synchronous_mode.py", line 60, in tick data[name] = self._get_sensor_data(q, timeout) File "/home/rlagent/rl/environments/carla/tools/synchronous_mode.py", line 83, in _get_sensor_data data = sensor_queue.get(timeout=timeout) File "/usr/lib/python3.8/queue.py", line 178, in get raise Empty _queue.Empty

How to solve this?