Run MobileSAM prompt segmentation on Arm Ethos-U85 with ExecuTorch
Introduction
Understand the MobileSAM deployment workflow
Prepare the ExecuTorch and Arm environment
Export MobileSAM for Ethos-U85
Build and run MobileSAM on the Corstone-320 FVP
Validate the MobileSAM segmentation result
Next Steps

  Log an issue

  Fork and edit

  Discuss on Discord

About this Learning Path

Skill level:  Introductory
Reading time:  45 min
Last updated:  10 Sep 2026
Skill level:
  Introductory
Reading time:
  45 min
Last updated:
  10 Sep 2026
Author:Usamah Zaheer, Arm
Arm IP:Ethos-U
Tags: ML Linux macOS ExecuTorch PyTorch MobileSAM Python CMake GCC FVP
Author:
  • Usamah Zaheer, Arm
Arm IP:
Ethos-U
Tags:
ML Linux macOS ExecuTorch PyTorch MobileSAM Python CMake GCC FVP

Who is this for?

This Learning Path is for embedded machine learning developers who want to evaluate transformer-based image segmentation on an Arm Ethos-U85 NPU with ExecuTorch.

What will you learn?

Upon completion of this Learning Path, you will be able to:

  • Identify how the MobileSAM example turns a fixed point prompt and an image into a quantized segmentation mask
  • Set up ExecuTorch and the Arm Ethos-U development tools
  • Export, build, and run the MobileSAM example on a Corstone-320 Fixed Virtual Platform (FVP)
  • Validate quantization quality, Ethos-U delegation, and target mask agreement

Prerequisites

Before starting, you will need the following:

  • A Linux development machine or an Apple silicon Mac
  • Familiarity with PyTorch model export and embedded cross-compilation

Summary

AI-assisted

This summary was drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
You’ll prepare MobileSAM, export a quantized fixed-prompt model for Ethos-U85, and build a bare-metal ExecuTorch application. Then, you’ll run prompt segmentation on the Corstone-320 FVP and save the target output. Finally, you’ll reconstruct the target mask and compare it with the host quantized mask. You’ll confirm that both validation stages meet the required intersection over union (IoU) threshold.

Frequently asked questions

AI-assisted

These FAQs were drafted with an approved AI-assisted workflow and reviewed by Arm contributors before publication. Human technical review remains part of the process so the final page reflects engineering rigor, accuracy, and Arm editorial standards.

Close
?
How do I know my host is supported before I start?
Run the preflight check to verify supported platforms and required tools, including python3.12, git, cmake, c++, and either Ninja or Make.
Which directory should I run commands from during export and build?
Run commands from the ExecuTorch repository root. Activate your Python environment and source examples/arm/arm-scratch/setup_path.sh in the current shell.
What should I expect after running the MobileSAM export step?
The script downloads the pinned MobileSAM revision, applies the patch for a configurable image size, and keeps the external source in a separate working directory. You should see exported assets referenced later, such as metadata under arm_test/mobilesam_manual/export/ and a reference quantized mask image.
What confirms that the FVP execution worked?
The example runs on the Corstone-320 FVP and produces a log file used for validation (for example, arm_test/mobilesam_manual/fvp.log). That log contains the encoded segmentation mask for the visualization tool to decode.
How do I validate the segmentation quality and target agreement?
Run the visualization tool with the FVP log, the example input image, the exported metadata JSON, and the reference quantized mask. The tool reconstructs the target mask and checks that the IoU meets the specified threshold, such as --minimum-iou=0.9.
Next