Hugging Face's logo

qualcomm
/
SINet

Image Segmentation
PyTorch
android
Model card Files
xet
 Community

SINet: Optimized for Qualcomm Devices

SINet is a machine learning model that is designed to segment people from close-up portrait images in real time.

This is based on the implementation of SINet 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

There are two ways to deploy this model on your device:

Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

Runtime Precision Chipset SDK Versions Download
ONNX float Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a16 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.1 Download
QNN_DLC float Universal QAIRT 2.43 Download
QNN_DLC w8a16 Universal QAIRT 2.43 Download
QNN_DLC w8a8 Universal QAIRT 2.43 Download
TFLITE float Universal QAIRT 2.43, TFLite 2.17.0 Download
TFLITE w8a8 Universal QAIRT 2.43, TFLite 2.17.0 Download

For more device-specific assets and performance metrics, visit SINet on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

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

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for SINet on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Model checkpoint: SINet.pth
  • Input resolution: 224x224
  • Number of output classes: 2 (foreground / background)
  • Number of parameters: 91.9K
  • Model size (float): 415 KB
  • Model size (w8a8): 241 KB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
SINet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.707 ms 0 - 40 MB NPU
SINet ONNX float Snapdragon® X2 Elite 0.77 ms 0 - 0 MB NPU
SINet ONNX float Snapdragon® X Elite 1.907 ms 2 - 2 MB NPU
SINet ONNX float Snapdragon® 8 Gen 3 Mobile 1.102 ms 0 - 45 MB NPU
SINet ONNX float Qualcomm® QCS8550 (Proxy) 1.662 ms 1 - 33 MB NPU
SINet ONNX float Qualcomm® QCS9075 2.139 ms 2 - 5 MB NPU
SINet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.859 ms 0 - 38 MB NPU
SINet ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.89 ms 0 - 46 MB NPU
SINet ONNX w8a16 Snapdragon® X2 Elite 0.971 ms 0 - 0 MB NPU
SINet ONNX w8a16 Snapdragon® X Elite 2.219 ms 1 - 1 MB NPU
SINet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.32 ms 0 - 61 MB NPU
SINet ONNX w8a16 Qualcomm® QCS6490 52.302 ms 14 - 17 MB CPU
SINet ONNX w8a16 Qualcomm® QCS8550 (Proxy) 1.96 ms 0 - 3 MB NPU
SINet ONNX w8a16 Qualcomm® QCS9075 2.242 ms 0 - 3 MB NPU
SINet ONNX w8a16 Qualcomm® QCM6690 19.68 ms 22 - 30 MB CPU
SINet ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 1.03 ms 0 - 39 MB NPU
SINet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 13.792 ms 22 - 31 MB CPU
SINet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.356 ms 0 - 41 MB NPU
SINet ONNX w8a8 Snapdragon® X2 Elite 3.509 ms 8 - 8 MB NPU
SINet ONNX w8a8 Snapdragon® X Elite 43.084 ms 7 - 7 MB NPU
SINet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 4.209 ms 7 - 64 MB NPU
SINet ONNX w8a8 Qualcomm® QCS6490 31.592 ms 7 - 10 MB CPU
SINet ONNX w8a8 Qualcomm® QCM6690 15.896 ms 7 - 15 MB CPU
SINet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 3.481 ms 0 - 38 MB NPU
SINet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 11.229 ms 7 - 15 MB CPU
SINet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.124 ms 1 - 39 MB NPU
SINet QNN_DLC float Snapdragon® X2 Elite 1.405 ms 1 - 1 MB NPU
SINet QNN_DLC float Snapdragon® X Elite 3.838 ms 1 - 1 MB NPU
SINet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.217 ms 0 - 47 MB NPU
SINet QNN_DLC float Qualcomm® QCS8275 (Proxy) 6.624 ms 1 - 36 MB NPU
SINet QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.464 ms 1 - 2 MB NPU
SINet QNN_DLC float Qualcomm® SA8775P 3.951 ms 1 - 38 MB NPU
SINet QNN_DLC float Qualcomm® QCS9075 3.853 ms 1 - 4 MB NPU
SINet QNN_DLC float Qualcomm® QCS8450 (Proxy) 3.722 ms 0 - 52 MB NPU
SINet QNN_DLC float Qualcomm® SA7255P 6.624 ms 1 - 36 MB NPU
SINet QNN_DLC float Qualcomm® SA8295P 4.726 ms 0 - 35 MB NPU
SINet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.832 ms 1 - 33 MB NPU
SINet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.196 ms 0 - 41 MB NPU
SINet QNN_DLC w8a16 Snapdragon® X2 Elite 3.538 ms 0 - 0 MB NPU
SINet QNN_DLC w8a16 Snapdragon® X Elite 7.033 ms 0 - 0 MB NPU
SINet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 4.072 ms 0 - 50 MB NPU
SINet QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 10.819 ms 0 - 37 MB NPU
SINet QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 6.552 ms 0 - 26 MB NPU
SINet QNN_DLC w8a16 Qualcomm® SA8775P 7.029 ms 0 - 40 MB NPU
SINet QNN_DLC w8a16 Qualcomm® QCS9075 6.832 ms 2 - 5 MB NPU
SINet QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 7.178 ms 0 - 53 MB NPU
SINet QNN_DLC w8a16 Qualcomm® SA7255P 10.819 ms 0 - 37 MB NPU
SINet QNN_DLC w8a16 Qualcomm® SA8295P 8.148 ms 0 - 35 MB NPU
SINet QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 3.439 ms 0 - 37 MB NPU
SINet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 2.133 ms 0 - 39 MB NPU
SINet QNN_DLC w8a8 Snapdragon® X2 Elite 2.453 ms 0 - 0 MB NPU
SINet QNN_DLC w8a8 Snapdragon® X Elite 4.585 ms 0 - 0 MB NPU
SINet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 2.802 ms 0 - 48 MB NPU
SINet QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 7.466 ms 0 - 36 MB NPU
SINet QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 4.217 ms 0 - 2 MB NPU
SINet QNN_DLC w8a8 Qualcomm® SA8775P 4.578 ms 0 - 39 MB NPU
SINet QNN_DLC w8a8 Qualcomm® QCS9075 4.603 ms 0 - 2 MB NPU
SINet QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 4.475 ms 0 - 49 MB NPU
SINet QNN_DLC w8a8 Qualcomm® SA7255P 7.466 ms 0 - 36 MB NPU
SINet QNN_DLC w8a8 Qualcomm® SA8295P 5.241 ms 0 - 34 MB NPU
SINet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.354 ms 0 - 35 MB NPU
SINet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.694 ms 0 - 38 MB NPU
SINet TFLITE float Snapdragon® 8 Gen 3 Mobile 1.094 ms 0 - 44 MB NPU
SINet TFLITE float Qualcomm® QCS8275 (Proxy) 3.78 ms 0 - 33 MB NPU
SINet TFLITE float Qualcomm® QCS8550 (Proxy) 1.68 ms 0 - 2 MB NPU
SINet TFLITE float Qualcomm® SA8775P 2.157 ms 0 - 36 MB NPU
SINet TFLITE float Qualcomm® QCS9075 2.095 ms 1 - 4 MB NPU
SINet TFLITE float Qualcomm® QCS8450 (Proxy) 1.994 ms 0 - 50 MB NPU
SINet TFLITE float Qualcomm® SA7255P 3.78 ms 0 - 33 MB NPU
SINet TFLITE float Qualcomm® SA8295P 2.545 ms 0 - 34 MB NPU
SINet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.847 ms 0 - 29 MB NPU
SINet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.638 ms 0 - 39 MB NPU
SINet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.033 ms 0 - 47 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS6490 26.189 ms 0 - 12 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 2.949 ms 0 - 35 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.475 ms 0 - 2 MB NPU
SINet TFLITE w8a8 Qualcomm® SA8775P 1.775 ms 0 - 38 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS9075 1.779 ms 0 - 3 MB NPU
SINet TFLITE w8a8 Qualcomm® QCM6690 16.847 ms 0 - 32 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.67 ms 0 - 47 MB NPU
SINet TFLITE w8a8 Qualcomm® SA7255P 2.949 ms 0 - 35 MB NPU
SINet TFLITE w8a8 Qualcomm® SA8295P 2.224 ms 0 - 34 MB NPU
SINet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.74 ms 0 - 39 MB NPU
SINet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 6.445 ms 0 - 35 MB NPU

License

  • The license for the original implementation of SINet can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Image Segmentation
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/SINet