# Run image classification with ExecuTorch on Alif E8 and Ethos-U85

## In this learning path

- [Introduction](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/)
- [Set up the Alif Ensemble E8 DevKit](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/board-setup/)
- [Compile the model on an Arm cloud instance](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/aws-ec2-setup/)
- [Create the image classification firmware project](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/create-project/)
- [Add the application code](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/application-code/)
- [Configure memory layout and flash settings](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/memory-configuration/)
- [Prepare a test image](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/image-preparation/)
- [Build, flash, and verify inference](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/build-flash-verify/)
- [Next Steps](https://learn.arm.com/learning-paths/embedded-and-microcontrollers/alif-image-classification/_next-steps/)

## About this Learning Path

|  |  |
| --- | --- |
| Skill level: | Advanced |
| Reading time: | 2 hrs |
| Last updated: | 12 Nov 2026 |

|  |  |
| --- | --- |
| Author: | Gabriel Peterson , Arm<br>[GitHub](https://github.com/gabrieldpeterson)<br>[LinkedIn](https://linkedin.com/in/gabrieldpeterson)<br>[Twitter](https://twitter.com/@gabedpeterson)<br>[corteximplant.com](https://corteximplant.com/@gabe) |
| Arm IP: | [Cortex-M](https://support.arm.com/?tab=compute-ip&Product%20Type=Microcontrollers) [Ethos-U](https://support.arm.com/?tab=compute-ip&Product%20Type=Neural%20Processing%20Units) |
| Tags: | [AI/ML](https://learn.arm.com/tag/ai-ml/) [Baremetal](https://learn.arm.com/tag/baremetal) [ExecuTorch](https://learn.arm.com/tag/executorch) [PyTorch](https://learn.arm.com/tag/pytorch) [GCC](https://learn.arm.com/tag/gcc) [CMSIS-Toolbox](https://learn.arm.com/tag/cmsis-toolbox) [Python](https://learn.arm.com/tag/python) |

## Who is this for?
This is an advanced topic for embedded developers who want to deploy a neural network model to an Arm Cortex-M55 microcontroller using ExecuTorch and an Ethos-U85 NPU.

## What will you learn?
After completing this Learning Path, you'll be able to perform the following tasks:
* Compile a MobileNetV2 model for the Ethos-U85 NPU using ExecuTorch's ahead-of-time (AOT) compiler on an Arm-based cloud instance
* Build ExecuTorch static libraries for bare-metal Cortex-M55 targets
* Configure CMSIS project files, memory layout, and linker scripts for an ML workload on the Alif Ensemble E8
* Run real-time image classification inference on the Ethos-U85 NPU and verify results using SEGGER Real-Time Transfer (RTT)

## Prerequisites
Before starting, you'll need the following prerequisites:
* Experience with C/C++ and embedded development concepts
* An [Alif Ensemble E8 DevKit](https://alifsemi.com/support/kits/ensemble-e8devkit/) with a USB-C cable
* A SEGGER J-Link debug probe (included in the DevKit)
* A development machine running macOS on Apple Silicon with Visual Studio Code installed
* An AWS account or access to an Arm-based cloud instance for native Arm compilation

## Summary
You’ll deploy a MobileNetV2 image classifier on the Alif Ensemble E8 DevKit by compiling the model and runtime for the Ethos-U85 NPU, building a CMSIS project, and running inference with SEGGER RTT output. First, you’ll validate the board, debug probe, and flashing workflow, then use an Arm-based cloud instance to produce ExecuTorch static libraries and an Ethos-U85–targeted model. Next, you’ll create an `mv2_runner` firmware project from the Blinky template, add the provided application code that initializes the NPU and executes inference on a test image, and integrate RTT for result reporting. Finally, you’ll make memory layout and linker updates so the model, runtime, and SRAM working set fit, enabling real-time classification on the device.
