YOLOv7-seg INT8 (V2)

Edge LinuxRaspberry Pi 5

This is an INT8-quantized version of YOLOv7-seg optimized for edge deployment on ARM devices using ExecuTorch with the XNNPACK backend. The model was quantized using PT2E static symmetric per-channel quantization and exported to the .pte format for efficient instance segmentation inference on ARM Cortex-A processors (Raspberry Pi, AWS Graviton, mobile ARM, embedded).View on Hugging Face

Accuracyvs base model

Mask mAP@0.50:0.9540.09%↓0.08 pp

Frames / sec

0.53fps

Latency

About this version

Original Model:: yolov7-seg by Not specified — yolov7-seg
Optimization/conversion:: Arm-Optimized version for execution on Arm-based platforms.
Converted/optimized by:: Arm
License:: The Original Model and the Optimized Model are subject to GPL-3.0-or-later.

This repository contains a converted or optimized version of the Original Model (the “Optimized Model”). The Original Model has been converted or optimized as described above for execution on Arm-based platforms.

No retraining or fine-tuning of the Original Model was performed as part of the conversion or optimization. The conversion or optimization was not intended to change the Original Model’s behavior or intended use.

Original Model and Documentation

For information about the Original Model, including its development, training data, intended uses, limitations and other relevant information, please refer to the Original Model repository. Information in that repository was provided by the original developer or other third parties and, unless expressly stated otherwise, has not been independently verified by Arm.

Licenses and Third-Party Terms

Use of the Original Model and the Optimized Model is subject to the applicable licenses, usage restrictions and other terms identified above and in the relevant repositories. Publication of the Optimized Model does not grant any rights beyond those provided under the applicable license terms.

You are responsible for reviewing those terms and ensuring that your use of the Original Model and the Optimized Model is permitted.

Purpose of this Release

About this version

Original Model:: yolov7-seg by Not specified — yolov7-seg
Optimization/conversion:: Arm-Optimized version for execution on Arm-based platforms.
Converted/optimized by:: Arm
License:: The Original Model and the Optimized Model are subject to GPL-3.0-or-later.

Original Model and Documentation

Licenses and Third-Party Terms

You are responsible for reviewing those terms and ensuring that your use of the Original Model and the Optimized Model is permitted.

Metric	Resultsvs baseline	Change
End to end latency p50	1880.52ms5046.22ms	−3165.70 ms
End to end latency p90	1883.47ms5051.16ms	−3167.69 ms
End to end latency p99	1884.78ms5060.04ms	−3175.26 ms
Peak memory	277.69MB520.83MB	−243.14 MB
Average memory	276.53MB519.98MB	−243.45 MB
Time to first inference	1944.38ms5870.04ms	−3925.66 ms
Frames per second	0.53fps0.20fps	+0.33 fps
Mask mAP@0.50	63.55%63.83%	−0.28%
Mask mAP@0.75	42.40%42.35%	+0.05%
Mask mAP@0.50:0.95	40.09%40.17%	−0.08%

Configuration	Baseline	Arm Optimized
Dataset	COCO 2017 (val2017)	COCO 2017 (val2017)
Sample count	5,000	5,000
Batch size	1	1
Input resolution	640x640	640x640
Runs	100	100
Warmup runs	10	10

YOLOv7-seg INT8 (V2)

YOLOv7-seg INT8 (V2)

Get Started with this Model

Deploy an MCP Server on Raspberry Pi 5 for AI agent interaction using OpenAI SDK

Model Evaluation

Configuration

Comparability