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 | 3.226 ms | 1 - 216 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite Mobile | 4.667 ms | 13 - 212 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X2 Elite | 3.615 ms | 16 - 16 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X Elite | 7.254 ms | 17 - 17 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X Elite | 7.254 ms | 17 - 17 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.878 ms | 15 - 248 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.492 ms | 12 - 19 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.667 ms | 13 - 212 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS9075 | 7.952 ms | 12 - 15 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.971 ms | 5 - 198 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 2.762 ms | 0 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 2.807 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 4.926 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 4.926 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.433 ms | 0 - 206 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.573 ms | 5 - 6 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.52 ms | 0 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.52 ms | 0 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.52 ms | 0 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 17.123 ms | 1 - 179 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.326 ms | 5 - 196 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 9.406 ms | 0 - 166 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.762 ms | 0 - 181 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 6.063 ms | 5 - 15 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.811 ms | 0 - 99 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.261 ms | 0 - 84 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3.02 ms | 0 - 109 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4.121 ms | 0 - 5 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8775P | 5.957 ms | 4 - 88 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8775P | 5.957 ms | 4 - 88 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8775P | 5.957 ms | 4 - 88 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA7255P | 16.329 ms | 4 - 83 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 8.618 ms | 4 - 87 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8295P | 8.67 ms | 4 - 61 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.261 ms | 0 - 84 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 5.844 ms | 4 - 23 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.