Failure to use TensorRT to detect objects in videos

Description

I can’t create an execution context in a Python program due to it not parsing the trt.engine file properly. I created this trt.engine file using a TAO Toolkit in notebook format.

Environment for the Engine Creation

TAO Toolkit Version: 5.0.0
Nvidia Driver Version: 551.23
Operating System + Version: Windows 11 WSL

Virtual Environment in Ubuntu 22.04.3 LTS
Package Version


anyio 4.0.0
argon2-cffi 23.1.0
argon2-cffi-bindings 21.2.0
arrow 1.3.0
asttokens 2.4.0
async-lru 2.0.4
attrs 23.1.0
Babel 2.13.0
backcall 0.2.0
beautifulsoup4 4.12.2
bleach 6.1.0
certifi 2023.7.22
cffi 1.16.0
chardet 3.0.4
charset-normalizer 3.3.0
click 8.1.7
comm 0.1.4
configparser 6.0.0
cycler 0.12.1
debugpy 1.8.0
decorator 5.1.1
defusedxml 0.7.1
docker 4.3.1
docker-pycreds 0.4.0
exceptiongroup 1.1.3
executing 2.0.0
fastjsonschema 2.18.1
fqdn 1.5.1
idna 2.10
ipykernel 6.25.2
ipython 8.16.1
ipython-genutils 0.2.0
ipywidgets 8.1.1
isoduration 20.11.0
jedi 0.19.1
Jinja2 3.1.2
json5 0.9.14
jsonpointer 2.4
jsonschema 4.19.1
jsonschema-specifications 2023.7.1
jupyter 1.0.0
jupyter_client 8.4.0
jupyter-console 6.6.3
jupyter_core 5.4.0
jupyter-events 0.8.0
jupyter-lsp 2.2.0
jupyter_server 2.8.0
jupyter_server_terminals 0.4.4
jupyterlab 4.0.7
jupyterlab-pygments 0.2.2
jupyterlab_server 2.25.0
jupyterlab-widgets 3.0.9
kiwisolver 1.4.5
MarkupSafe 2.1.3
matplotlib 3.3.3
matplotlib-inline 0.1.6
mistune 3.0.2
nbclient 0.8.0
nbconvert 7.9.2
nbformat 5.9.2
nest-asyncio 1.5.8
notebook 7.0.6
notebook_shim 0.2.3
numpy 1.26.1
nvidia-pyindex 1.0.9
nvidia-tao 5.1.0
nvidia-tao-client 5.2.0
overrides 7.4.0
packaging 23.2
pandocfilters 1.5.0
parso 0.8.3
pexpect 4.8.0
pickleshare 0.7.5
Pillow 10.1.0
pip 23.3.1
platformdirs 3.11.0
prometheus-client 0.17.1
prompt-toolkit 3.0.39
psutil 5.9.6
ptyprocess 0.7.0
pure-eval 0.2.2
pycparser 2.21
Pygments 2.16.1
pyparsing 3.1.1
python-dateutil 2.8.2
python-json-logger 2.0.7
PyYAML 6.0.1
pyzmq 25.1.1
qtconsole 5.4.4
QtPy 2.4.0
referencing 0.30.2
requests 2.31.0
rfc3339-validator 0.1.4
rfc3986-validator 0.1.1
rpds-py 0.10.6
Send2Trash 1.8.2
setuptools 68.2.0
six 1.15.0
sniffio 1.3.0
soupsieve 2.5
stack-data 0.6.3
tabulate 0.8.7
terminado 0.17.1
tinycss2 1.2.1
tomli 2.0.1
tornado 6.3.3
traitlets 5.11.2
types-python-dateutil 2.8.19.14
typing_extensions 4.8.0
uri-template 1.3.0
urllib3 1.26.18
wcwidth 0.2.8
webcolors 1.13
webencodings 0.5.1
websocket-client 0.57.0
wheel 0.41.2
widgetsnbextension 4.0.9

Steps To Reproduce

  1. Activate a new virtualenvwrapper in Ubuntu and open the notebook within the environment.
  2. In the notebook, navigate to the directory of the downloaded TAO Toolkit, and then open tao_launcher_starter_kit/yolov4_tiny/yolo_v4_tiny.ipynb
  3. Train and export a non-QAT model, and then convert it into a TRT engine.
  4. Run a python program attached that uses the TRT engine.
    detection.txt (1.7 KB)

Traceback:
C:\Users\kbclm\AppData\Local\Programs\Python\Python37\python.exe “C:\Users\kbclm\Downloads\GrandSlam AI\main.py”
[01/29/2024-13:33:00] [TRT] [E] 1: [pluginV2Runner.cpp::nvinfer1::rt::load::300] Error Code 1: Serialization (Serialization assertion creator failed.Cannot deserialize plugin since corresponding IPluginCreator not found in Plugin Registry)
[01/29/2024-13:33:00] [TRT] [E] 4: [runtime.cpp::nvinfer1::Runtime::deserializeCudaEngine::66] Error Code 4: Internal Error (Engine deserialization failed.)
Traceback (most recent call last):
File “C:\Users\kbclm\Downloads\GrandSlam AI\main.py”, line 15, in
context = engine.create_execution_context()
AttributeError: ‘NoneType’ object has no attribute ‘create_execution_context’

There is no update from you for a period, assuming this is not an issue anymore. Hence we are closing this topic. If need further support, please open a new one. Thanks

Please try official deepstream_tao_apps github against the videos. GitHub - NVIDIA-AI-IOT/deepstream_tao_apps: Sample apps to demonstrate how to deploy models trained with TAO on DeepStream.

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.