# Python AI Application Development on Genio 1200 with Yocto or Ubuntu **URL:** \ **Category:** NeuroPilot - Analytical AI\ **Tags:** Ubuntu, AI, Genio-1200, IoT-Yocto\ **Created:** [May 6, 2026, 11:04am UTC](https://genio-community.mediatek.com/t/python-ai-application-development-on-genio-1200-with-yocto-or-ubuntu/2233 "2026-05-06T11:04:33Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Sting\_Cheng](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/sting_cheng/32/506_2.png) [@Sting\_Cheng](https://genio-community.mediatek.com/u/Sting_Cheng)\ **Post date:** [May 6, 2026, 11:04am UTC](https://genio-community.mediatek.com/t/python-ai-application-development-on-genio-1200-with-yocto-or-ubuntu/2233/1 "2026-05-06T11:04:34Z")
I would like to integrate analytical AI applications in python on Genio 1200 with Yocto and Ubuntu. I’ve found - in my python program, in spite of using “/usr/sbin/neuronrt” command, I am not able to launch neuron runtime and ONNX Runtime (missing NeuronExecutionProvider) - I am not able to find /usr/sbin/neuronrt and related neuron libraries in Ubuntu Can you please tell me where to download these missing (python) packages and software component and how I can install them on my Genio 1200 with both Yocto and Ubuntu operating system ? ---
**Author:** ![Jun](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/jun/32/532_2.png) [@Jun](https://genio-community.mediatek.com/u/Jun)\ **Post date:** [May 12, 2026, 7:55am UTC](https://genio-community.mediatek.com/t/python-ai-application-development-on-genio-1200-with-yocto-or-ubuntu/2233/3 "2026-05-12T07:55:19Z")
Hi Sting\_Cheng, Thanks for reaching out! Here is a quick summary of the **Analytical AI** framework support on Genio 1200: - On Yocto: both **Neuron Runtime** and **ONNX Runtime** are supported. - On Ubuntu: only **Neuron Runtime** is supported; ONNX Runtime is currently not supported. For more details about platform support, please refer to the [AI Supporting Scope](https://mediatek.gitlab.io/genio/doc/iot-aihub/master/ai_hub/overview.html#ai-supporting-scope) To run Neuron Runtime on Ubuntu, you will need to install the `mtk-neuropilot` package from the Snap Store. This [page](https://mediatek.gitlab.io/genio/doc/iot-aihub/master/ai_hub/supported_os/ubuntu.html#ubuntu) describes how to install NeuroPilot on Ubuntu and walks through the AI workflow. Best, Jun ---
**Author:** ![Sting\_Cheng](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/sting_cheng/32/506_2.png) [@Sting\_Cheng](https://genio-community.mediatek.com/u/Sting_Cheng)\ **Post date:** [May 15, 2026, 6:31am UTC](https://genio-community.mediatek.com/t/python-ai-application-development-on-genio-1200-with-yocto-or-ubuntu/2233/4 "2026-05-15T06:31:27Z")
Hi Jun, Many thanks for your input, I have the following further questions, hope you can provide some hints for my reference. - What do you mean by “Neuron Runtime”, do you mean using neuronrt command on Yocto or Ubuntu ? - As for ONNX Runtime on yocto, does the python onnx runtime currently support CPU only? I’ve tried the following python code snippet with error > genio\_onnx\_inference.py > > import numpy as np > import onnxruntime as ort > import time > > def run\_genio\_onnx\_inference(model\_path): > available\_providers = ort.get\_available\_providers() > print(f"Available Providers: {available\_providers}") > > ``` > if 'NeuronExecutionProvider' not in available_providers: > print("Warning: NeuronEP not found. Ensure libonnxruntime_providers_neuron.so is in LD_LIBRARY_PATH.") > selected_providers = \['CPUExecutionProvider'\] > else: > > ``` > > $ python3 ./genio\_onnx\_inference.py > Available Providers: [‘XnnpackExecutionProvider’, ‘CPUExecutionProvider’] > Warning: NeuronEP not found. Ensure libonnxruntime\_providers\_neuron.so is in LD\_LIBRARY\_PATH. > Session creation failed: [ONNXRuntimeError] : 3 : NO\_SUCHFILE : Load model from resnet50\_optimized.onnx failed:Load model resnet50\_optimized.onnx failed. File doesn’t exist ---
**Author:** ![Sting\_Cheng](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/sting_cheng/32/506_2.png) [@Sting\_Cheng](https://genio-community.mediatek.com/u/Sting_Cheng)\ **Post date:** [May 20, 2026, 7:33am UTC](https://genio-community.mediatek.com/t/python-ai-application-development-on-genio-1200-with-yocto-or-ubuntu/2233/5 "2026-05-20T07:33:48Z")
I’ve been trying to neuronrt on my ubuntu with the following error message /snap/mtk-neuropilot/10/usr/sbin/neuronrt -m hw -a /home/sting/test3/yolov8s-quant/yolov8s\_biv\_quant\_mdla2.0.dla -i ./temp\_input\_640.bin -o ./temp\_out1.bin -o ./temp\_out2.bin -o ./temp\_out3.bin -o ./temp\_out4.bin -b 100 INFO: dlopen libneuronusdk\_runtime.mtk.so Can’t open config file ERROR: Getting configuration data failed. WARNING: Cannot create device for MDLA\_2\_0 WARNING: Found an unsupported target: MDLA\_2\_0 ERROR: Cannot prepare execution. ERROR: Successfully load network but cannot start execution. ERROR: Runtime loadNetworkFromFile fails. ERROR: Cannot load model from file /home/sting/test3/yolov8s-quant/yolov8s\_biv\_quant\_mdla2.0.dla ERROR: Read dla fail ---
**Author:** ![Jun](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/jun/32/532_2.png) [@Jun](https://genio-community.mediatek.com/u/Jun)\ **Post date:** [May 27, 2026, 9:52am UTC](https://genio-community.mediatek.com/t/python-ai-application-development-on-genio-1200-with-yocto-or-ubuntu/2233/7 "2026-05-27T09:52:35Z")
**[Q1] What does “Neuron Runtime” mean?** Neuron Runtime is an independent **offline inference path** that directly executes compiled `.dla` models on the NPU. The `neuronrt` command is the CLI tool of this path. In contrast, online inference is handled by **TFLite Interpreter** or **ONNX Runtime** , which delegate execution to CPU / GPU / NPU backends. For more details, you can check our software architecture page: [Software Architecture](https://mediatek.gitlab.io/genio/doc/iot-aihub/master/ai_hub/software_architecture.html#software-architecture) * * * **[Q2] Does Python ONNX Runtime on Yocto only support CPU?** Yes — on **Genio 1200** , ONNX Runtime currently supports the **CPU backend only**. For the per-platform support matrix, please refer to [Supporting Scope on Yocto](https://mediatek.gitlab.io/genio/doc/iot-aihub/master/ai_hub/supported_os/yocto.html#supporting-scope-on-yocto) To collect performance numbers on the CPU backend, you can run: ```bash python3 /usr/share/onnxruntime_example/label_image.py --model efficientnet-lite4.onnx ``` * * * **[Q3] `neuronrt` failure on Ubuntu (snap)** Before digging into the log, could you share the following so we can check on our side? 1. The **Ubuntu image version** running on your Genio 1200. 2. The **mtk-neuropilot snap version and channel** : ```bash snap list mtk-neuropilot snap info mtk-neuropilot ``` Best, Jun ---
**Author:** ![Sting\_Cheng](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/sting_cheng/32/506_2.png) [@Sting\_Cheng](https://genio-community.mediatek.com/u/Sting_Cheng)\ **Post date:** [May 28, 2026, 3:36am UTC](https://genio-community.mediatek.com/t/python-ai-application-development-on-genio-1200-with-yocto-or-ubuntu/2233/8 "2026-05-28T03:36:41Z")
Hi June, The followings are my feedback to [Q2] and [Q3]. **[Q2] Does Python ONNX Runtime on Yocto only support CPU?** The current yocto on my Genio 1200 is scarthgap\_k6.6\_v25.1.1\_genio-1200-evk. there seems to be no /usr/share/onnxruntime\_benchmark on my genio ? ~# python3 /usr/share/onnxruntime\_benchmark/onnxruntime\_benchmark.py --auto python3: can’t open file ‘/usr/share/onnxruntime\_benchmark/onnxruntime\_benchmark.py’: [Errno 2] No such file or directory **[Q3] `neuronrt` failure on Ubuntu (snap)** $ snap list mtk-neuropilot Name Version Rev Tracking Publisher Notes mtk-neuropilot 7.1+g20250723.e1f31314 10 latest/edge asaly12 - $ snap info mtk-neuropilot name: mtk-neuropilot summary: APU firmware and demo app for Mediatek Genio 1200 publisher: Asal Mirzaieva (asaly12) store-url: [Install mtk-neuropilot on Linux | Snap Store](https://snapcraft.io/mtk-neuropilot) license: unset description: | Enables Mediatek Genio board’s APU and provides a standard “label\_image” demo app to test it. commands: - mtk-neuropilot.apu-mdw-test - mtk-neuropilot.benchmark - mtk-neuropilot.demo - mtk-neuropilot.edma-test - mtk-neuropilot.label-image-armnn-delegate - mtk-neuropilot.label-image-gpu-external-delegate-prebuilt - mtk-neuropilot.mdla2-player - mtk-neuropilot.mdla3-player - mtk-neuropilot.nnstreamer-example-face-detection - mtk-neuropilot.nnstreamer-example-image-classification - mtk-neuropilot.nnstreamer-example-low-light-image-enhancement - mtk-neuropilot.nnstreamer-example-monocular-depth-estimation - mtk-neuropilot.nnstreamer-example-object-detection - mtk-neuropilot.nnstreamer-example-object-detection-yolov5 - mtk-neuropilot.nnstreamer-example-pose-estimation - mtk-neuropilot.vpu5-test snap-id: sSP0CEc0Io9eD9pJOkvB1CKLb3s3GXMN tracking: latest/edge refresh-date: 8 days ago, at 05:55 UTC channels: latest/stable: – latest/candidate: 7.0+g20250430.e1f31314 2025-05-28 (9) 258MB - latest/beta: ↑ latest/edge: 7.1+g20250723.e1f31314 2025-07-23 (10) 561MB - installed: 7.1+g20250723.e1f31314 (10) 561MB - ---
**Author:** ![Jun](https://yyz2.discourse-cdn.com/flex004/user_avatar/genio-community.mediatek.com/jun/32/532_2.png) [@Jun](https://genio-community.mediatek.com/u/Jun)\ **Post date:** [May 28, 2026, 9:44am UTC](https://genio-community.mediatek.com/t/python-ai-application-development-on-genio-1200-with-yocto-or-ubuntu/2233/9 "2026-05-28T09:44:03Z")
Hi Sting\_Cheng, Quick correction on my Q2 — I’ve also updated the original reply for the record. To be precise, on **Genio 1200** , ONNX Runtime currently supports the **CPU backend only**. You can check the per-platform support matrix here: [Supporting Scope on Yocto](https://mediatek.gitlab.io/genio/doc/iot-aihub/master/ai_hub/supported_os/yocto.html#supporting-scope-on-yocto) If you are using the `scarthgap_k6.6_v25.1.1_genio-1200-evk` image, you can verify the CPU backend performance with: ```bash python3 /usr/share/onnxruntime_example/label_image.py --model efficientnet-lite4.onnx ``` Best, Jun