README.md

---
library_name: pytorch
license: other
tags:
- real_time
- android
pipeline_tag: image-segmentation

---

![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/yolov8_seg/web-assets/model_demo.png)

# YOLOv8-Segmentation: Optimized for Qualcomm Devices

Ultralytics YOLOv8 is a machine learning model that predicts bounding boxes, segmentation masks and classes of objects in an image.

This is based on the implementation of YOLOv8-Segmentation found [here](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/segment).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/yolov8_seg) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.

## Getting Started
Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/yolov8_seg) Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations

See our repository for [YOLOv8-Segmentation on GitHub](https://github.com/qualcomm/ai-hub-models/blob/v0.59.0/src/qai_hub_models/models/yolov8_seg) for usage instructions.


## Model Details

**Model Type:** Model_use_case.semantic_segmentation

**Model Stats:**
- Model checkpoint: YOLOv8N-Seg
- Input resolution: 640x640
- Number of output classes: 80
- Number of parameters: 3.43M
- Model size (float): 13.2 MB
- Model size (w8a16): 3.91 MB

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X2 Elite | 3.754 ms | 17 - 17 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X Elite | 7.107 ms | 17 - 17 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.953 ms | 17 - 241 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 12.533 ms | 17 - 221 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.589 ms | 1 - 113 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS8450 | 12.533 ms | 17 - 221 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 9.069 ms | 17 - 20 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 7.107 ms | 17 - 17 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.743 ms | 12 - 203 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 4.743 ms | 12 - 203 MB | NPU
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.257 ms | 12 - 225 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 2.885 ms | 5 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 5.018 ms | 5 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.475 ms | 5 - 213 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 9.4 ms | 5 - 198 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8275 | 17.129 ms | 1 - 181 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.648 ms | 5 - 112 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.505 ms | 0 - 181 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 6.505 ms | 0 - 181 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 6.505 ms | 0 - 181 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 9.4 ms | 5 - 198 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.253 ms | 5 - 15 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.018 ms | 5 - 5 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.801 ms | 5 - 185 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 17.129 ms | 1 - 181 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 9.391 ms | 0 - 166 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.801 ms | 5 - 185 MB | NPU
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.048 ms | 5 - 200 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.026 ms | 0 - 108 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 8.65 ms | 4 - 89 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8275 | 16.278 ms | 4 - 82 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.06 ms | 4 - 6 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8775P | 6.002 ms | 4 - 86 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8650P | 6.002 ms | 4 - 86 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8255P | 6.002 ms | 4 - 86 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 8.65 ms | 4 - 89 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 5.714 ms | 4 - 23 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.269 ms | 0 - 84 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA7255P | 16.278 ms | 4 - 82 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8295P | 8.669 ms | 4 - 60 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.269 ms | 0 - 84 MB | NPU
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.881 ms | 0 - 92 MB | NPU

## License
* The license for the original implementation of YOLOv8-Segmentation can be found
  [here](https://github.com/ultralytics/ultralytics/blob/main/LICENSE).

## References
* [Ultralytics YOLOv8 Docs: Instance Segmentation](https://docs.ultralytics.com/tasks/segment/)
* [Source Model Implementation](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/models/yolo/segment)

## Community
* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).