# Running GestureNet model on Holoscan **URL:** \ **Category:** TAO Toolkit\ **Tags:** tensorrt\ **Created:** [December 22, 2025, 2:58pm UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445 "2025-12-22T14:58:39Z")\ **Posts on this page:** 10\ **Page:** 1
**Author:** ![nvipwan1](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@nvipwan1](https://forums.developer.nvidia.com/u/nvipwan1)\ **Post date:** [December 22, 2025, 2:58pm UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/1 "2025-12-22T14:58:39Z")
Hi , I have been trying to run gestureNet model from NGC to run on AGX ORIN. Downloaded from following link > **[GPU-optimized AI, Machine Learning, & HPC Software | NVIDIA NGC | NVIDIA NGC](https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/gesturenet)** > > GPU-optimized AI, Machine Learning, & HPC Software | NVIDIA NGC It has a file model.eltl . I’m unable to convert it to ONNX or TENSORRT engine . Could you anyone help with steps on how to convert eltl model to tesorrt engine on AGX ORIN and run it using holoscan . My AGX Orin is running JP 6.2.1 Also does the model work with Holoscan ---
**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\ **Post date:** [December 27, 2025, 3:00pm UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/2 "2025-12-27T15:00:02Z")
@nvipwan1 Moving this topic from GPU-Accelerated Libraries forum to TAO forum since this .etlt model is released by TAO. ---
**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\ **Post date:** [December 27, 2025, 3:04pm UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/3 "2025-12-27T15:04:07Z")
Please refer to [tao\_toolkit\_recipes/tao\_forum\_faq/FAQ.md at main · NVIDIA-AI-IOT/tao\_toolkit\_recipes · GitHub](https://github.com/NVIDIA-AI-IOT/tao_toolkit_recipes/blob/main/tao_forum_faq/FAQ.md#tlt-or-etlt) to convert the .etlt model to .onnx file. Then use trtexec to convert the .onnx file to tensorrt engine. Refer to [TRTEXEC with Classification TF1/TF2/PyT — Tao Toolkit](https://docs.nvidia.com/tao/tao-toolkit/6.0.0/text/trtexec_integration/trtexec_classification_ds.html#sample-command-for-a-classification-tf1-tf2-pyt-model). ---
**Author:** ![nvipwan1](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@nvipwan1](https://forums.developer.nvidia.com/u/nvipwan1)\ **Post date:** [January 8, 2026, 10:21am UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/4 "2026-01-08T10:21:03Z")
Hi , When I run the command on AGX Orin from the link you have provided _$ docker run --runtime=nvidia -it --rm -v /home/morganh:/home/morganh [nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5](http://nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5) /bin/bash_ I’m getting following error \*Status: Downloaded newer image for [nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5](http://nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5) WARNING: The requested image’s platform (linux/amd64) does not match the detected host platform (linux/arm64/v8) and no specific platform was requested exec /opt/nvidia/nvidia\_entrypoint.sh: exec format error \* Is there any way I can convert eltl on AGX Orin ---
**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\ **Post date:** [January 9, 2026, 8:43am UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/5 "2026-01-09T08:43:17Z")
> [@nvipwan1](#): > > \*Status: Downloaded newer image for [nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5](http://nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5) > WARNING: The requested image’s platform (linux/amd64) does not match the detected host platform (linux/arm64/v8) and no specific platform was requested > exec /opt/nvidia/nvidia\_entrypoint.sh: exec format error For the command of `$ docker run --runtime=nvidia -it --rm -v /home/morganh:/home/morganh nvcr.io/nvidia/tao/tao-toolkit:5.0.0-tf1.15.5 /bin/bash`, it is needed to run in x86-based machine instead of Jetson devices. For Jetson devices, you can run trtexec inside a l4t docker to generate the engine. For example, Jetpack6.0 + [nvcr.io/nvidia/l4t-tensorrt:r8.5.2.2-devel](http://nvcr.io/nvidia/l4t-tensorrt:r8.5.2.2-devel). BTW, for how to use tao-deploy in Jetson devices, please take a look at [Cannot use TAO Deploy in Jetson AGX Orin - #5 by Morganh](https://forums.developer.nvidia.com/t/cannot-use-tao-deploy-in-jetson-agx-orin/315225/5). ---
**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\ **Post date:** [January 12, 2026, 3:26am UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/6 "2026-01-12T03:26:31Z")
More, to convert .etlt to .onnx file, please run with a dgpu machine instead of Jetson devices. ---
**Author:** ![nvipwan1](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@nvipwan1](https://forums.developer.nvidia.com/u/nvipwan1)\ **Post date:** [January 28, 2026, 7:23am UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/7 "2026-01-28T07:23:31Z")
Hi, I followed the steps outlined on GitHub for x86 with a dGPU and was able to access the Docker command line successfully. I also downloaded the `.eltl` file and created the Python script as described in the GitHub documentation. However, after running the script, the `.onnx` file is not being generated, and no errors are reported during execution. Could you please help me understand what might be going wrong? Thanks. ---
**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\ **Post date:** [January 28, 2026, 8:45am UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/8 "2026-01-28T08:45:36Z")
Is there write-access in your path? More, is the key correct, `nvidia_tlt` according to `https://catalog.ngc.nvidia.com/orgs/nvidia/teams/tao/models/gesturenet?version=deployable_v2.0.2`. You can also add debug into the code to check further. ---
**Author:** ![nvipwan1](https://developer.download.nvidia.com/images/forums/profile-default-devtalk-84.png) [@nvipwan1](https://forums.developer.nvidia.com/u/nvipwan1)\ **Post date:** [January 30, 2026, 9:15am UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/9 "2026-01-30T09:15:08Z")
Hi, Yes there is write access in the path, I’m able to create files using touch command and write data to the file. Yes I’m using write passkey. How can I add debug info to the script ? Should I add prints ? or any other way to debug ? ---
**Author:** ![Morganh](https://sea2.discourse-cdn.com/nvidia/user_avatar/forums.developer.nvidia.com/morganh/32/9748_2.png) [@Morganh](https://forums.developer.nvidia.com/u/Morganh)\ **Post date:** [February 1, 2026, 3:21pm UTC](https://forums.developer.nvidia.com/t/running-gesturenet-model-on-holoscan/355445/10 "2026-02-01T15:21:51Z")
> [@nvipwan1](#): > > Should I add prints Yes, you can add some prints.