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® 8 Elite Gen 5 Mobile | 2.957 ms | 0 - 233 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X2 Elite | 3.432 ms | 16 - 16 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X Elite | 6.862 ms | 17 - 17 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.095 ms | 17 - 290 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.374 ms | 12 - 23 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS9075 | 7.788 ms | 13 - 16 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.319 ms | 2 - 227 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.893 ms | 5 - 189 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 2.802 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 4.861 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.322 ms | 5 - 215 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 16.916 ms | 1 - 180 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.455 ms | 5 - 48 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.353 ms | 0 - 182 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 6.043 ms | 5 - 15 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.943 ms | 5 - 196 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 16.916 ms | 1 - 180 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 9.2 ms | 0 - 165 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.648 ms | 5 - 189 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.755 ms | 0 - 103 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.92 ms | 0 - 110 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 16.156 ms | 4 - 84 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.989 ms | 0 - 2 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8775P | 5.871 ms | 4 - 90 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 5.779 ms | 4 - 23 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 8.866 ms | 4 - 208 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA7255P | 16.156 ms | 4 - 84 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8295P | 8.625 ms | 4 - 174 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.247 ms | 0 - 80 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.