Hugging Face's logo

qualcomm
/
MediaPipe-Selfie-Segmentation

Image Segmentation
PyTorch
android
Model card Files
xet
Community

MediaPipe-Selfie-Segmentation: Optimized for Qualcomm Devices

Light-weight model that segments a person from the background in square or landscape selfie and video conference imagery.

This is based on the implementation of MediaPipe-Selfie-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

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 2.37, ONNX Runtime 1.23.0 Download
ONNX w8a16 Universal QAIRT 2.37, ONNX Runtime 1.23.0 Download
ONNX w8a8 Universal QAIRT 2.37, ONNX Runtime 1.23.0 Download
QNN_DLC float Universal QAIRT 2.42 Download
QNN_DLC w8a16 Universal QAIRT 2.42 Download
QNN_DLC w8a8 Universal QAIRT 2.42 Download
TFLITE float Universal QAIRT 2.42, TFLite 2.17.0 Download
TFLITE w8a8 Universal QAIRT 2.42, TFLite 2.17.0 Download

For more device-specific assets and performance metrics, visit MediaPipe-Selfie-Segmentation 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 MediaPipe-Selfie-Segmentation on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.semantic_segmentation

Model Stats:

  • Model checkpoint: Square
  • Input resolution (Square): 256x256
  • Input resolution (Landscape): 144x256
  • Number of output classes: 6
  • Number of parameters: 106K
  • Model size (float): 447 KB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® X Elite 1.007 ms 2 - 2 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® 8 Gen 3 Mobile 0.679 ms 0 - 103 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Qualcomm® QCS8550 (Proxy) 1.049 ms 0 - 35 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Qualcomm® QCS9075 1.312 ms 1 - 4 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.574 ms 0 - 95 MB NPU
MediaPipe-Selfie-Segmentation ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.506 ms 0 - 97 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® X Elite 1.051 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.762 ms 0 - 108 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCS6490 25.813 ms 16 - 20 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCS8550 (Proxy) 1.1 ms 0 - 4 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCS9075 1.333 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Qualcomm® QCM6690 15.535 ms 15 - 21 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.592 ms 0 - 102 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 10.342 ms 15 - 22 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.519 ms 0 - 103 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® X Elite 0.499 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.356 ms 0 - 104 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCS6490 13.813 ms 7 - 11 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.523 ms 0 - 105 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCS9075 0.696 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Qualcomm® QCM6690 5.683 ms 7 - 15 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.309 ms 0 - 99 MB NPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 4.034 ms 0 - 8 MB CPU
MediaPipe-Selfie-Segmentation ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.287 ms 0 - 98 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® X Elite 0.838 ms 1 - 1 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.461 ms 0 - 37 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS8275 (Proxy) 1.773 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS8550 (Proxy) 0.698 ms 0 - 11 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® SA8775P 0.988 ms 1 - 28 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS9075 0.852 ms 1 - 3 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® QCS8450 (Proxy) 0.958 ms 0 - 38 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® SA7255P 1.773 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Qualcomm® SA8295P 1.309 ms 1 - 25 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.36 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.327 ms 1 - 31 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® X Elite 0.806 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.474 ms 0 - 36 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS6490 1.995 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS8275 (Proxy) 1.466 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS8550 (Proxy) 0.678 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® SA8775P 0.886 ms 0 - 28 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS9075 0.771 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCM6690 2.341 ms 0 - 138 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® QCS8450 (Proxy) 0.801 ms 0 - 39 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® SA7255P 1.466 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Qualcomm® SA8295P 1.165 ms 0 - 24 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.354 ms 0 - 27 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 0.671 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 0.29 ms 0 - 31 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® X Elite 0.385 ms 0 - 0 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.182 ms 0 - 31 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS6490 0.782 ms 2 - 4 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 0.706 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.264 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® SA8775P 0.441 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS9075 0.375 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCM6690 0.835 ms 0 - 22 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.337 ms 0 - 34 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® SA7255P 0.706 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Qualcomm® SA8295P 0.62 ms 0 - 21 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.147 ms 0 - 22 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.258 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.137 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Snapdragon® 8 Gen 3 Mobile 0.466 ms 0 - 34 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS8275 (Proxy) 1.791 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS8550 (Proxy) 0.705 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® SA8775P 1.01 ms 0 - 28 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS9075 0.87 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® QCS8450 (Proxy) 0.965 ms 0 - 37 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® SA7255P 1.791 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Qualcomm® SA8295P 1.366 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.367 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.33 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.186 ms 0 - 30 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS6490 0.735 ms 0 - 3 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 0.723 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.265 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® SA8775P 0.459 ms 0 - 25 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS9075 0.361 ms 0 - 2 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCM6690 0.837 ms 0 - 20 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.349 ms 0 - 32 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® SA7255P 0.723 ms 0 - 23 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Qualcomm® SA8295P 0.624 ms 0 - 20 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.15 ms 0 - 26 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.268 ms 0 - 21 MB NPU
MediaPipe-Selfie-Segmentation TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.141 ms 0 - 25 MB NPU

License

  • The license for the original implementation of MediaPipe-Selfie-Segmentation 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