ramanathan831
commented
1 year ago can you post in general Nvidia tao forum, this is not a colab issue https://forums.developer.nvidia.com/c/accelerated-computing/intelligent-video-analytics/tao-toolkit/17
Good morning, I tried to create a docker container for using tao-deploy, starting from official nvidia container nvidia/cuda:12.1.1-cudnn8-devel-ubuntu22.04
Next, following the tao-deploy container and setup_env_colab.sh script I installed all the python packages.
When I tried to convert PeopleNet model to TensorRT engine with the following command
detectnet_v2 gen_trt_engine -m /home/ngc_content/ptm_models/peoplenet_vpruned_v2.3/resnet34_peoplenet_pruned.etlt -k $KEY -e $trt_experiment_spec --data_type $data_type --batch_size 1 --max_batch_size 1 --engine_file $trt_out_file_name
following the indications of colab container I got the following error:
Loading uff directly from the package source code Traceback (most recent call last): File "/usr/local/bin/detectnet_v2", line 8, in
sys.exit(main())
File "", line 12, in main
File "", line 196, in launch_job
File "", line 50, in get_modules
File "/usr/lib/python3.8/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "", line 1014, in _gcd_import
File "", line 991, in _find_and_load
File "", line 975, in _find_and_load_unlocked
File "", line 671, in _load_unlocked
File "", line 843, in exec_module
File "", line 219, in _call_with_frames_removed
File "</usr/local/lib/python3.8/dist-packages/nvidia_tao_deploy/cv/detectnet_v2/scripts/gen_trt_engine.py>", line 3, in
File "", line 19, in
File "</usr/local/lib/python3.8/dist-packages/nvidia_tao_deploy/cv/detectnet_v2/engine_builder.py>", line 1, in
File "", line 38, in
File "</usr/local/lib/python3.8/dist-packages/nvidia_tao_deploy/engine/builder.py>", line 1, in
File "", line 28, in
ValueError: not enough values to unpack (expected 4, got 3)
Any suggestions?
Regards