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. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up 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 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 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 | 3.633 ms | 17 - 17 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X Elite | 6.937 ms | 17 - 17 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.911 ms | 17 - 241 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 12.422 ms | 17 - 221 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 7.444 ms | 15 - 22 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS8450 | 12.422 ms | 17 - 221 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 9.012 ms | 16 - 18 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.209 ms | 0 - 217 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 4.66 ms | 12 - 204 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 4.66 ms | 12 - 204 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 6.937 ms | 17 - 17 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 2.845 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 4.908 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.414 ms | 0 - 206 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 9.312 ms | 5 - 199 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 | 17.107 ms | 0 - 180 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.577 ms | 5 - 13 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.482 ms | 1 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8650P | 6.482 ms | 1 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8255P | 6.482 ms | 1 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 | 9.312 ms | 5 - 199 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 6.225 ms | 7 - 17 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.045 ms | 5 - 201 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 17.107 ms | 0 - 180 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.777 ms | 0 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 9.405 ms | 1 - 167 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 2.777 ms | 0 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 4.908 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.017 ms | 0 - 108 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 8.583 ms | 5 - 91 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8275 | 16.303 ms | 4 - 81 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.082 ms | 0 - 2 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8775P | 5.954 ms | 4 - 87 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8650P | 5.954 ms | 4 - 87 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8255P | 5.954 ms | 4 - 87 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8450 | 8.583 ms | 5 - 91 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 6.332 ms | 4 - 23 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.889 ms | 0 - 92 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA7255P | 16.303 ms | 4 - 81 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.274 ms | 0 - 84 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8295P | 8.684 ms | 4 - 61 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.274 ms | 0 - 84 MB | NPU |
License
- The license for the original implementation of YOLOv8-Segmentation can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.