Skip to content
ModelListedExternal
Download

YOLOv8 Seg

This version of YOLOv8-Seg has been converted to run on the Axera NPU using w8a16 quantization.

Sourcehuggingface.co/AXERA-TECH/YOLOv8-Seg/tree/6cb7ad455fa1bcf65a3a48bb9c0541625fdf2999
KindOtherBase modelUltralytics/YOLOv8VersionRevision 6cb7ad4Dgrade

Model source

Kind
Other
File size
13.1–274 MB
Base model
Ultralytics/YOLOv8
Version
vRevision 6cb7ad4
Updated
Oct 21, 2026
Downloads
33
Source
Hugging Face

Source description

YOLOv8-Seg

This version of YOLOv8-Seg has been converted to run on the Axera NPU using w8a16 quantization.

This model has been optimized with the following LoRA:

Compatible with Pulsar2 version: 5.0

Convert tools links:

For those who are interested in model conversion, you can try to export axmodel through

Support Platform

Performance Statistics

AX650N

ModelLatency(ms) npu1Latency(ms) npu3
yolov8n-seg5.0961.847
yolov8s-seg13.7244.735
yolov8m-seg34.58211.912
yolov8l-seg65.27522.312
yolov8x-seg110.20836.147

AX630C

ModelLatency(ms) npu1Latency(ms) npu2
yolov8n-seg18.56112.036
yolov8s-seg38.49330.259
yolov8m-seg94.77969.217
yolov8l-seg179.964121.261
yolov8x-seg296.999190.418

AX615

ModelLatency(ms) npu1Latency(ms) npu2
yolov8n-seg22.02413.867
yolov8s-seg62.06835.333
yolov8m-seg160.45086.186

AX637

ModelLatency(ms) npu1
yolov8n-seg6.175
yolov8s-seg15.654
yolov8m-seg35.612
yolov8l-seg67.062
yolov8x-seg104.862

How to use

Download all files from this repository to the device

Inference

Input image:

Inference with AX650 Host, such as M4N-Dock(爱芯派Pro)

(base) root@ax650:~/ax650seg# python3 ax_infer.py --model-path yolov8m-seg_640x640_npu3.axmodel --test-img bus.jpg
[INFO] Using provider: AxEngineExecutionProvider
[INFO] Chip type: ChipType.MC50
[INFO] VNPU type: VNPUType.DISABLED
[INFO] Engine version: 2.12.0s
[INFO] Model type: 2 (triple core)
[INFO] Compiler version: 6.0-dirty a498e20d-dirty
[YOLOv8-Seg] [15:38:19.398] [DEBUG] Load model time = 592.02 ms
[YOLOv8-Seg] [15:38:19.433] [DEBUG] Pre-process time = 8.17 ms
[YOLOv8-Seg] [15:38:19.472] [DEBUG] Forward time = 38.19 ms
[YOLOv8-Seg] [15:38:19.482] [DEBUG] Post-process time = 9.47 ms
[YOLOv8-Seg] [15:38:19.483] [DEBUG] Proto shape: (32, 160, 160)
[YOLOv8-Seg] [15:38:19.534] [INFO] Draw Results (6 objects):
[YOLOv8-Seg] [15:38:19.535] [INFO] (13, 230, 803, 736) -> bus: 0.93
[YOLOv8-Seg] [15:38:19.580] [INFO] (49, 398, 244, 904) -> person: 0.91
[YOLOv8-Seg] [15:38:19.599] [INFO] (222, 397, 345, 860) -> person: 0.89
[YOLOv8-Seg] [15:38:19.616] [INFO] (667, 395, 810, 880) -> person: 0.88
[YOLOv8-Seg] [15:38:19.632] [INFO] (0, 551, 78, 866) -> person: 0.59
[YOLOv8-Seg] [15:38:19.647] [INFO] (137, 472, 148, 504) -> tie: 0.37
[YOLOv8-Seg] [15:38:19.685] [INFO] Saved to result_yolov8_seg.jpg

Output image:

Sources

1 source
Hugging FacePrimaryVersion 6cb7ad455fa1bcf65a3a48bb9c0541625fdf2999
huggingface.co/AXERA-TECH/YOLOv8-Seg/tree/6cb7ad455fa1bcf65a3a48bb9c0541625fdf2999

Verified Oct 21

Model artifacts

5 artifacts

yolov8l-seg_640x640.onnx

onnx · 175 MB · SHA-256 2b317e94a6ac…c175 · Hugging Face

Download

yolov8m-seg_640x640.onnx

onnx · 104 MB · SHA-256 b2381143275c…8faf · Hugging Face

Download

yolov8n-seg_640x640.onnx

onnx · 13.1 MB · SHA-256 924de98d6bb9…74b3 · Hugging Face

Download

yolov8s-seg_640x640.onnx

onnx · 45.1 MB · SHA-256 330f3943b419…d06a · Hugging Face

Download

yolov8x-seg_640x640.onnx

onnx · 274 MB · SHA-256 d6b88d24056e…92fb · Hugging Face

Download

Source excerpts

3 excerpts
ReadmeAug 5huggingface.co/AXERA-TECH/YOLOv8-Seg

--- license: mit language: - en base_model: - Ultralytics/YOLOv8 pipeline_tag: object-detection tags: - Ultralytics - YOLOv8 - YOLOv8-Seg --- # YOLOv8-Seg This version of YOLOv8-Seg has been converted to run on the Axera NPU using **w8a16** quantization. This model has been optimized with the following LoRA: Compatible with Pulsar2 version: 5.0 ## Convert tools links: For those who are interested in model conversion, you can try to export axmodel through - [The repo of AXera Platform](https://github.com/AXERA-TECH/ax-samples), which you can get the detial of guide - [Pulsar2 Link, How to Convert ONNX to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/pulsar2/introduction.html) ## Support Platform - **AX650N/AX8850** - [M4N-Dock(爱芯派Pro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html) - [M.2 Accelerator card](https://docs.m5stack.com/en/ai_hardware/LLM-8850_Card) - **AX630C** - [爱芯派2](https://axera-pi-2-docs-cn.readthedocs.io/zh-cn/latest/index.html) - [Module-LLM](https://docs.m5stack.com/zh_CN/module/Module-LLM) - [LLM630 Compute Kit](https://docs.m5stack.com/zh_CN/core/LLM630%20Compute%20Kit) - **AX615** - **AX637** ### Performance Statistics #### AX650N | Model | Latency(ms) npu1 | Latency(ms) npu3 | | :--- | :---: | :---: | | **yolov8n-seg** | 5.096 | 1.847 | | **yolov8s-seg** | 13.724 | 4.735 | | **yolov8m-seg** | 34.582 | 11.912 | | **yolov8l-seg** | 65.275 | 22.312 | | **yolov8x-seg** | 110.208 | 36.147 | #### AX630C | Model | Latency(ms) npu1 | Latency(ms) npu2 | | :--- | :---: | :---: | | **yolov8n-seg** | 18.561 | 12.036 | | **yolov8s-seg** | 38.493 | 30.259 | | **yolov8m-seg** | 94.779 | 69.217 | | **yolov8l-seg** | 179.964 | 121.261 | | **yolov8x-seg** | 296.999 | 190.418 | #### AX615 | Model | Latency(ms) npu1 | Latency(ms) npu2 | | :--- | :---: | :---: | | **yolov8n-seg** | 22.024 | 13.867 | | **yolov8s-seg** | 62.068 | 35.333 | | **yolov8m-seg** | 160.450 | 86.186 | #### AX637 | Model | Latency(ms) npu1 | | :--- | :---: | | **yolov8n-seg** | 6.175 | | **yolov8s-seg** | 15.654 | | **yolov8m-seg** | 35.612 | | **yolov8l-seg** | 67.062 | | **yolov8x-seg** | 104.862 | ## How to use Download all files from this repository to the device ### Inference Input image: ![](./bus.jpg) #### Inference with AX650 Host, such as M4N-Dock(爱芯派Pro) ``` (base) root@ax650:~/ax650seg# python3 ax_infer.py --model...

ReadmeJul 16huggingface.co/AXERA-TECH/YOLOv8-Seg

--- license: mit language: - en base_model: - Ultralytics/YOLOv8 pipeline_tag: object-detection tags: - Ultralytics - YOLOv8 - YOLOv8-Seg --- # YOLOv8-Seg This version of YOLOv8-Seg has been converted to run on the Axera NPU using **w8a16** quantization. This model has been optimized with the following LoRA: Compatible with Pulsar2 version: 5.0 ## Convert tools links: For those who are interested in model conversion, you can try to export axmodel through - [The repo of AXera Platform](https://github.com/AXERA-TECH/ax-samples), which you can get the detial of guide - [Pulsar2 Link, How to Convert ONNX to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/pulsar2/introduction.html) ## Support Platform - **AX650N/AX8850** - [M4N-Dock(爱芯派Pro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html) - [M.2 Accelerator card](https://docs.m5stack.com/en/ai_hardware/LLM-8850_Card) - **AX630C** - [爱芯派2](https://axera-pi-2-docs-cn.readthedocs.io/zh-cn/latest/index.html) - [Module-LLM](https://docs.m5stack.com/zh_CN/module/Module-LLM) - [LLM630 Compute Kit](https://docs.m5stack.com/zh_CN/core/LLM630%20Compute%20Kit) - **AX615** - **AX637** ### Performance Statistics #### AX650N | Model | Latency(ms) npu1 | Latency(ms) npu3 | | :--- | :---: | :---: | | **yolo26n-seg** | 5.096 | 1.847 | | **yolo26s-seg** | 13.724 | 4.735 | | **yolo26m-seg** | 34.582 | 11.912 | | **yolo26l-seg** | 65.275 | 22.312 | | **yolo26x-seg** | 110.208 | 36.147 | #### AX630C | Model | Latency(ms) npu1 | Latency(ms) npu2 | | :--- | :---: | :---: | | **yolo26n-seg** | 18.561 | 12.036 | | **yolo26s-seg** | 38.493 | 30.259 | | **yolo26m-seg** | 94.779 | 69.217 | | **yolo26l-seg** | 179.964 | 121.261 | | **yolo26x-seg** | 296.999 | 190.418 | #### AX615 | Model | Latency(ms) npu1 | Latency(ms) npu2 | | :--- | :---: | :---: | | **yolo26n-seg** | 22.024 | 13.867 | | **yolo26s-seg** | 62.068 | 35.333 | | **yolo26m-seg** | 160.450 | 86.186 | #### AX637 | Model | Latency(ms) npu1 | | :--- | :---: | | **yolo26n-seg** | 6.175 | | **yolo26s-seg** | 15.654 | | **yolo26m-seg** | 35.612 | | **yolo26l-seg** | 67.062 | | **yolo26x-seg** | 104.862 | ## How to use Download all files from this repository to the device ### Inference Input image: ![](./bus.jpg) #### Inference with AX650 Host, such as M4N-Dock(爱芯派Pro) ``` (base) root@ax650:~/ax650seg# python3 ax_infer.py --model...

ReadmeJul 11huggingface.co/AXERA-TECH/YOLOv8-Seg

--- license: mit language: - en base_model: - Ultralytics/YOLOv8 pipeline_tag: object-detection tags: - Ultralytics - YOLOv8 - YOLOv8-Seg --- # YOLOv8-Seg This version of YOLOv8-Seg has been converted to run on the Axera NPU using **w8a16** quantization. This model has been optimized with the following LoRA: Compatible with Pulsar2 version: 5.0 ## Convert tools links: For those who are interested in model conversion, you can try to export axmodel through - [The repo of AXera Platform](https://github.com/AXERA-TECH/ax-samples), which you can get the detial of guide - [Pulsar2 Link, How to Convert ONNX to axmodel](https://pulsar2-docs.readthedocs.io/en/latest/pulsar2/introduction.html) ## Support Platform - **AX650N/AX8850** - [M4N-Dock(爱芯派Pro)](https://wiki.sipeed.com/hardware/zh/maixIV/m4ndock/m4ndock.html) - [M.2 Accelerator card](https://docs.m5stack.com/en/ai_hardware/LLM-8850_Card) - **AX630C** - [爱芯派2](https://axera-pi-2-docs-cn.readthedocs.io/zh-cn/latest/index.html) - [Module-LLM](https://docs.m5stack.com/zh_CN/module/Module-LLM) - [LLM630 Compute Kit](https://docs.m5stack.com/zh_CN/core/LLM630%20Compute%20Kit) - **AX615** - **AX637** ### Performance Statistics #### AX650N | Model | Latency(ms) npu1 | Latency(ms) npu3 | | :--- | :---: | :---: | | **yolo26n-seg** | - | - | | **yolo26s-seg** | - | - | | **yolo26m-seg** | - | - | | **yolo26l-seg** | - | - | | **yolo26x-seg** | - | - | #### AX630C | Model | Latency(ms) npu1 | Latency(ms) npu2 | | :--- | :---: | :---: | | **yolo26n-seg** | - | - | | **yolo26s-seg** | - | - | | **yolo26m-seg** | - | - | | **yolo26l-seg** | - | - | | **yolo26x-seg** | - | - | #### AX615 | Model | Latency(ms) npu1 | Latency(ms) npu2 | | :--- | :---: | :---: | | **yolo26n-seg** | - | - | | **yolo26s-seg** | - | - | | **yolo26m-seg** | - | - | | **yolo26l-seg** | - | - | | **yolo26x-seg** | - | - | #### AX637 | Model | Latency(ms) npu1 | | :--- | :---: | | **yolo26n-seg** | - | | **yolo26s-seg** | - | | **yolo26m-seg** | - | | **yolo26l-seg** | - | | **yolo26x-seg** | - | ## How to use Download all files from this repository to the device ### Inference Input image: ![](./bus.jpg) #### Inference with AX650 Host, such as M4N-Dock(爱芯派Pro) ``` (base) root@ax650:~/ax650seg# python3 ax_infer.py --model-path yolov8m-seg_640x640_npu3.axmodel --test-img bus.jpg [INFO] Using provider: AxEngineExecutionProv...