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 | 2.955 ms | 0 - 233 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X2 Elite | 3.453 ms | 16 - 16 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® X Elite | 6.865 ms | 17 - 17 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 4.061 ms | 16 - 295 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.354 ms | 12 - 19 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Qualcomm® QCS9075 | 7.797 ms | 13 - 16 MB | NPU |
| YOLOv8-Segmentation | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.306 ms | 0 - 221 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.916 ms | 5 - 189 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X2 Elite | 2.783 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® X Elite | 4.853 ms | 5 - 5 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 3.339 ms | 5 - 216 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 16.948 ms | 0 - 179 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 4.486 ms | 5 - 38 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8775P | 6.379 ms | 1 - 182 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS9075 | 6.047 ms | 5 - 15 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 9.859 ms | 5 - 195 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA7255P | 16.948 ms | 0 - 179 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Qualcomm® SA8295P | 9.217 ms | 0 - 165 MB | NPU |
| YOLOv8-Segmentation | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.66 ms | 0 - 183 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 1.751 ms | 0 - 102 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.92 ms | 0 - 113 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 16.149 ms | 4 - 84 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 3.97 ms | 0 - 2 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8775P | 23.111 ms | 4 - 88 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS9075 | 5.77 ms | 4 - 23 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 8.899 ms | 4 - 207 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA7255P | 16.149 ms | 4 - 84 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Qualcomm® SA8295P | 8.653 ms | 4 - 174 MB | NPU |
| YOLOv8-Segmentation | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.257 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.
