Run roslaunch viplanner_node viplanner.launch in the docker environment, the m2f_inference.py meet error

[tenthousandrain]

The error messages: NODES / pathFollower (path_follower/path_follower_node) viplanner_node (viplanner_node/viplanner_node.py)

auto-starting new master process[master]: started with pid [193] ROS_MASTER_URI=http://localhost:11311

setting /run_id to 9869e4a6-3dcb-11ef-a3cb-48b02dea7a8a process[rosout-1]: started with pid [206] started core service [/rosout] process[pathFollower-2]: started with pid [213] process[viplanner_node-3]: started with pid [214] /root/.local/lib/python3.8/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: warn(f"Failed to load image Python extension: {e}") /usr/lib/python3/dist-packages/requests/init.py:89: RequestsDependencyWarning: urllib3 (2.2.2) or chardet (3.0.4) doesn't match a supported version! warnings.warn("urllib3 ({}) or chardet ({}) doesn't match a supported " [Warning] Pre-trained ResNet50 models cannot be used since detectron2 not found [Warning] Pre-trained ResNet50 models cannot be used since mask2former not found [INFO] [1720513017.604229]: Get param viplanner_node/main_freq [INFO] [1720513017.607299]: Get param viplanner_node/image_flip [INFO] [1720513017.610182]: Get param viplanner_node/conv_dist [INFO] [1720513017.613056]: Get param viplanner_node/max_depth [INFO] [1720513017.615842]: Get param viplanner_node/overlap_ratio_thres [INFO] [1720513017.618825]: Get param viplanner_node/depth_zero_ratio_thres [INFO] [1720513017.621779]: Get param viplanner_node/model_save [INFO] [1720513017.624566]: Get param viplanner_node/m2f_cfg_file [INFO] [1720513017.627485]: Get param viplanner_node/m2f_model_path [INFO] [1720513017.630301]: Get param viplanner_node/depth_topic [INFO] [1720513017.633150]: Get param viplanner_node/depth_info_topic [INFO] [1720513017.635897]: Get param viplanner_node/rgb_topic [INFO] [1720513017.638585]: Get param viplanner_node/rgb_info_topic [INFO] [1720513017.657058]: Get param viplanner_node/goal_topic [INFO] [1720513017.660632]: Get param viplanner_node/path_topic [INFO] [1720513017.666303]: Get param viplanner_node/m2f_timer_topic [INFO] [1720513017.673315]: Get param viplanner_node/depth_uint_type [INFO] [1720513017.677351]: Get param viplanner_node/compressed [INFO] [1720513017.687420]: Get param viplanner_node/mount_cam_frame [INFO] [1720513017.692036]: Get param viplanner_node/robot_id [INFO] [1720513017.715265]: Get param viplanner_node/world_id [INFO] [1720513017.719250]: Get param viplanner_node/is_fear_act [INFO] [1720513017.722186]: Get param viplanner_node/buffer_size [INFO] [1720513017.725277]: Get param viplanner_node/angular_thread [INFO] [1720513017.728445]: Get param viplanner_node/track_dist [INFO] [1720513017.731409]: Get param viplanner_node/joyGoal_scale Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 109, in getattr value = super().getattr(name) File "/usr/local/lib/python3.8/dist-packages/addict/addict.py", line 67, in getattr return self.getitem(item) File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 138, in getitem return self.build_lazy(super().getitem(key)) File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 105, in missing raise KeyError(name) KeyError: 'layer_cfg'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "/root/catkin_ws/devel/lib/viplanner_node/viplanner_node.py", line 15, in exec(compile(fh.read(), python_script, 'exec'), context) File "/root/catkin_ws/src/viplanner/ros/planner/src/viplanner_node.py", line 1035, in node = VIPlannerNode(args) File "/root/catkin_ws/src/viplanner/ros/planner/src/viplanner_node.py", line 65, in init self.m2f_inference = Mask2FormerInference( File "/root/catkin_ws/src/viplanner/ros/planner/src/m2f_inference.py", line 32, in init self.model = init_detector(config_file, checkpoint_file, device="cuda:0") File "/root/.local/lib/python3.8/site-packages/mmdet/apis/inference.py", line 66, in init_detector model = MODELS.build(config.model) File "/usr/local/lib/python3.8/dist-packages/mmengine/registry/registry.py", line 570, in build return self.build_func(cfg, args, kwargs, registry=self) File "/usr/local/lib/python3.8/dist-packages/mmengine/registry/build_functions.py", line 232, in build_model_from_cfg return build_from_cfg(cfg, registry, default_args) File "/usr/local/lib/python3.8/dist-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg obj = obj_cls(args) # type: ignore File "/root/.local/lib/python3.8/site-packages/mmdet/models/detectors/mask2former.py", line 22, in init super().init( File "/root/.local/lib/python3.8/site-packages/mmdet/models/detectors/maskformer.py", line 36, in init self.panoptic_head = MODELS.build(panoptichead) File "/usr/local/lib/python3.8/dist-packages/mmengine/registry/registry.py", line 570, in build return self.build_func(cfg, args, kwargs, registry=self) File "/usr/local/lib/python3.8/dist-packages/mmengine/registry/build_functions.py", line 232, in build_model_from_cfg return build_from_cfg(cfg, registry, default_args) File "/usr/local/lib/python3.8/dist-packages/mmengine/registry/build_functions.py", line 121, in build_from_cfg obj = obj_cls(args) # type: ignore File "/root/.local/lib/python3.8/site-packages/mmdet/models/dense_heads/mask2former_head.py", line 104, in init self.num_heads = transformer_decoder.layer_cfg.cross_attn_cfg.num_heads File "/usr/local/lib/python3.8/dist-packages/mmengine/config/config.py", line 113, in getattr raise AttributeError(f"'{self.class.name}' object has no " AttributeError: 'ConfigDict' object has no attribute 'layer_cfg' [viplanner_node-3] process has died [pid 214, exit code 1, cmd /root/catkin_ws/devel/lib/viplanner_node/viplanner_node.py __name:=viplanner_node __log:=/root/.ros/log/9869e4a6-3dcb-11ef-a3cb-48b02dea7a8a/viplanner_node-3.log]. log file: /root/.ros/log/9869e4a6-3dcb-11ef-a3cb-48b02dea7a8a/viplanner_node-3*.log ^C[pathFollower-2] killing on exit [rosout-1] killing on exit [master] killing on exit shutting down processing monitor... ... shutting down processing monitor complete done root@ubuntu:~/catkin_ws/devel#

[pascal-roth]

Hi,

Thanks for using our work. This looks a lot like a version issue for me. Can you tell me which version of mmengine are you using?

[tenthousandrain]

Thanks for your reply! This is the version of mmengine in the docker: mmcv 2.0.0 mmdet 3.3.0 mmengine 0.10.4

[tenthousandrain]

Hi,

Thanks for using our work. This looks a lot like a version issue for me. Can you tell me which version of mmengine are you using?

I'm sorry, but is there any solution to slove this error?

[pascal-roth]

The mmcv version seems correct. At the time of the project, the corresponding versions were: mmdet 3.1.0 mmengine 0.8.4

Please check if these changes fix your issues.

[pascal-roth]

I assume the issue has been fixed. Closing it now due to inactivity. Please reopen in the case the issue still persists