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® X2 Elite 0.815 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 1.128 ms 0 - 46 MB NPU
SINet ONNX float Qualcomm® QCS8550 (Proxy) 1.664 ms 1 - 43 MB NPU
SINet ONNX float Qualcomm® QCS9075 2.141 ms 2 - 5 MB NPU
SINet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.856 ms 0 - 29 MB NPU
SINet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.708 ms 0 - 41 MB NPU
SINet ONNX w8a16 Snapdragon® X2 Elite 0.961 ms 0 - 0 MB NPU
SINet ONNX w8a16 Snapdragon® X Elite 2.214 ms 1 - 1 MB NPU
SINet ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 1.318 ms 0 - 53 MB NPU
SINet ONNX w8a16 Qualcomm® QCS6490 51.811 ms 13 - 16 MB CPU
SINet ONNX w8a16 Qualcomm® QCS8550 (Proxy) 1.953 ms 0 - 3 MB NPU
SINet ONNX w8a16 Qualcomm® QCS9075 2.229 ms 0 - 3 MB NPU
SINet ONNX w8a16 Qualcomm® QCM6690 19.972 ms 21 - 29 MB CPU
SINet ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 1.032 ms 0 - 38 MB NPU
SINet ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 13.662 ms 20 - 29 MB CPU
SINet ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.891 ms 0 - 46 MB NPU
SINet ONNX w8a8 Snapdragon® X2 Elite 3.443 ms 8 - 8 MB NPU
SINet ONNX w8a8 Snapdragon® X Elite 40.351 ms 7 - 7 MB NPU
SINet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 4.189 ms 7 - 64 MB NPU
SINet ONNX w8a8 Qualcomm® QCS6490 40.935 ms 7 - 10 MB CPU
SINet ONNX w8a8 Qualcomm® QCM6690 16.266 ms 7 - 14 MB CPU
SINet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 3.45 ms 0 - 40 MB NPU
SINet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 11.213 ms 7 - 16 MB CPU
SINet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 3.381 ms 0 - 42 MB NPU
SINet QNN_DLC float Snapdragon® X2 Elite 1.401 ms 1 - 1 MB NPU
SINet QNN_DLC float Snapdragon® X Elite 3.863 ms 1 - 1 MB NPU
SINet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 2.222 ms 0 - 47 MB NPU
SINet QNN_DLC float Qualcomm® QCS8275 (Proxy) 6.634 ms 1 - 34 MB NPU
SINet QNN_DLC float Qualcomm® QCS8550 (Proxy) 3.474 ms 1 - 3 MB NPU
SINet QNN_DLC float Qualcomm® SA8775P 3.934 ms 1 - 38 MB NPU
SINet QNN_DLC float Qualcomm® QCS9075 3.865 ms 3 - 6 MB NPU
SINet QNN_DLC float Qualcomm® QCS8450 (Proxy) 3.718 ms 0 - 52 MB NPU
SINet QNN_DLC float Qualcomm® SA7255P 6.634 ms 1 - 34 MB NPU
SINet QNN_DLC float Qualcomm® SA8295P 4.719 ms 1 - 36 MB NPU
SINet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.84 ms 1 - 33 MB NPU
SINet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 1.123 ms 1 - 39 MB NPU
SINet QNN_DLC w8a16 Snapdragon® X2 Elite 3.575 ms 0 - 0 MB NPU
SINet QNN_DLC w8a16 Snapdragon® X Elite 7.112 ms 0 - 0 MB NPU
SINet QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 4.07 ms 0 - 51 MB NPU
SINet QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 10.806 ms 0 - 39 MB NPU
SINet QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 6.533 ms 0 - 2 MB NPU
SINet QNN_DLC w8a16 Qualcomm® SA8775P 7.024 ms 0 - 39 MB NPU
SINet QNN_DLC w8a16 Qualcomm® QCS9075 6.835 ms 0 - 3 MB NPU
SINet QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 7.116 ms 0 - 52 MB NPU
SINet QNN_DLC w8a16 Qualcomm® SA7255P 10.806 ms 0 - 39 MB NPU
SINet QNN_DLC w8a16 Qualcomm® SA8295P 8.156 ms 0 - 35 MB NPU
SINet QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 3.44 ms 0 - 41 MB NPU
SINet QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 3.197 ms 0 - 42 MB NPU
SINet QNN_DLC w8a8 Snapdragon® X2 Elite 2.495 ms 0 - 0 MB NPU
SINet QNN_DLC w8a8 Snapdragon® X Elite 4.583 ms 0 - 0 MB NPU
SINet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 2.805 ms 0 - 49 MB NPU
SINet QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 7.504 ms 0 - 37 MB NPU
SINet QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 4.21 ms 0 - 66 MB NPU
SINet QNN_DLC w8a8 Qualcomm® SA8775P 4.573 ms 0 - 38 MB NPU
SINet QNN_DLC w8a8 Qualcomm® QCS9075 4.598 ms 2 - 4 MB NPU
SINet QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 4.479 ms 0 - 49 MB NPU
SINet QNN_DLC w8a8 Qualcomm® SA7255P 7.504 ms 0 - 37 MB NPU
SINet QNN_DLC w8a8 Qualcomm® SA8295P 5.258 ms 0 - 34 MB NPU
SINet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 2.354 ms 0 - 35 MB NPU
SINet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 2.135 ms 0 - 39 MB NPU
SINet TFLITE float Snapdragon® 8 Gen 3 Mobile 1.085 ms 0 - 44 MB NPU
SINet TFLITE float Qualcomm® QCS8275 (Proxy) 3.795 ms 0 - 33 MB NPU
SINet TFLITE float Qualcomm® QCS8550 (Proxy) 1.675 ms 0 - 2 MB NPU
SINet TFLITE float Qualcomm® SA8775P 2.153 ms 0 - 36 MB NPU
SINet TFLITE float Qualcomm® QCS9075 2.122 ms 1 - 4 MB NPU
SINet TFLITE float Qualcomm® QCS8450 (Proxy) 2.047 ms 0 - 49 MB NPU
SINet TFLITE float Qualcomm® SA7255P 3.795 ms 0 - 33 MB NPU
SINet TFLITE float Qualcomm® SA8295P 2.598 ms 0 - 34 MB NPU
SINet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.846 ms 0 - 30 MB NPU
SINet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.692 ms 0 - 38 MB NPU
SINet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 1.033 ms 0 - 47 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS6490 21.089 ms 0 - 12 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 3.053 ms 0 - 36 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 1.474 ms 0 - 2 MB NPU
SINet TFLITE w8a8 Qualcomm® SA8775P 7.587 ms 0 - 36 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS9075 1.791 ms 0 - 3 MB NPU
SINet TFLITE w8a8 Qualcomm® QCM6690 17.499 ms 0 - 32 MB NPU
SINet TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.682 ms 0 - 48 MB NPU
SINet TFLITE w8a8 Qualcomm® SA7255P 3.053 ms 0 - 36 MB NPU
SINet TFLITE w8a8 Qualcomm® SA8295P 2.216 ms 0 - 34 MB NPU
SINet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.742 ms 0 - 39 MB NPU
SINet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 6.6 ms 0 - 35 MB NPU
SINet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.635 ms 0 - 39 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