No module named 'clip_trt'

[UserName-wang]

Hi, environment: Jetson AGX Orin (32GB), JetPack 6 (L4T r36.2.0)

I tried command in container created by image dustynv/nano_llm:humble-r36.3.0. but got error message : jetson-containers run $(autotag nano_llm:humble) / ros2 launch ros2_nanollm camera_input_example.launch.py

ros2 launch ros2_nanollm camera_input_example.launch.py [INFO] [launch]: All log files can be found below /home/vscode/.ros/log/2024-08-20-14-38-27-259604-ubuntu-5879 [INFO] [launch]: Default logging verbosity is set to INFO [INFO] [cam2image-1]: process started with pid [5887] [INFO] [nano_llm_py-2]: process started with pid [5889] [cam2image-1] [ WARN:[email protected]] global cap_gstreamer.cpp:1728 open OpenCV | GStreamer warning: Cannot query video position: status=0, value=-1, duration=-1 [nano_llm_py-2] /usr/local/lib/python3.10/dist-packages/transformers/utils/hub.py:127: FutureWarning: Using TRANSFORMERS_CACHE is deprecated and will be removed in v5 of Transformers. Use HF_HOME instead. [nano_llm_py-2] warnings.warn( [nano_llm_py-2] Traceback (most recent call last): [nano_llm_py-2] File "/ros2_nanollm/install/ros2_nanollm/lib/ros2_nanollm/nano_llm_py", line 33, in [nano_llm_py-2] sys.exit(load_entry_point('ros2-nanollm', 'console_scripts', 'nano_llm_py')()) [nano_llm_py-2] File "/ros2_nanollm/install/ros2_nanollm/lib/ros2_nanollm/nano_llm_py", line 25, in importlib_load_entry_point [nano_llm_py-2] return next(matches).load() [nano_llm_py-2] File "/usr/lib/python3.10/importlib/metadata/init.py", line 171, in load [nano_llm_py-2] module = import_module(match.group('module')) [nano_llm_py-2] File "/usr/lib/python3.10/importlib/init.py", line 126, in import_module [nano_llm_py-2] return _bootstrap._gcd_import(name[level:], package, level) [nano_llm_py-2] File "", line 1050, in _gcd_import [nano_llm_py-2] File "", line 1027, in _find_and_load [nano_llm_py-2] File "", line 1006, in _find_and_load_unlocked [nano_llm_py-2] File "", line 688, in _load_unlocked [nano_llm_py-2] File "", line 883, in exec_module [nano_llm_py-2] File "", line 241, in _call_with_frames_removed [nano_llm_py-2] File "/ros2_nanollm/build/ros2_nanollm/ros2_nanollm/nano_llm_py.py", line 22, in [nano_llm_py-2] from nano_llm import NanoLLM, ChatHistory [nano_llm_py-2] File "/opt/NanoLLM/nano_llm/init.py", line 2, in [nano_llm_py-2] from .nano_llm import NanoLLM [nano_llm_py-2] File "/opt/NanoLLM/nano_llm/nano_llm.py", line 15, in [nano_llm_py-2] from .vision import CLIPVisionModel, TIMMVisionModel, MMProjector [nano_llm_py-2] File "/opt/NanoLLM/nano_llm/vision/init.py", line 3, in [nano_llm_py-2] from .clip import CLIPVisionModel, TIMMVisionModel [nano_llm_py-2] File "/opt/NanoLLM/nano_llm/vision/clip.py", line 3, in [nano_llm_py-2] from clip_trt import CLIPVisionModel, TIMMVisionModel [nano_llm_py-2] ModuleNotFoundError: No module named 'clip_trt' [ERROR] [nano_llm_py-2]: process has died [pid 5889, exit code 1, cmd '/ros2_nanollm/install/ros2_nanollm/lib/ros2_nanollm/nano_llm_py --ros-args --params-file /tmp/launch_params_vzf2a889']. [cam2image-1] [INFO] [1724164710.656228295] [cam2image]: Publishing image #1 [cam2image-1] [INFO] [1724164710.715841248] [cam2image]: Publishing image #2 [cam2image-1] [INFO] [1724164710.787807475] [cam2image]: Publishing image #3 [cam2image-1] [INFO] [1724164710.863811224] [cam2image]: Publishing image #4

Can you please help? thank you!