Hugging Face's logo

qualcomm
/
Shufflenet-v2

Image Classification
PyTorch
android
Model card Files
xet
Community

Shufflenet-v2: Optimized for Qualcomm Devices

ShufflenetV2 is a machine learning model that can classify images from the Imagenet dataset. It can also be used as a backbone in building more complex models for specific use cases.

This is based on the implementation of Shufflenet-v2 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 w8a8 Universal QAIRT 2.37, ONNX Runtime 1.23.0 Download
QNN_DLC float 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 Shufflenet-v2 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 Shufflenet-v2 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Model checkpoint: Imagenet
  • Input resolution: 224x224
  • Number of parameters: 1.37M
  • Model size (float): 5.24 MB
  • Model size (w8a8): 1.47 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
Shufflenet-v2 ONNX float Snapdragon® X Elite 0.94 ms 2 - 2 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Gen 3 Mobile 0.603 ms 0 - 107 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS8550 (Proxy) 0.991 ms 0 - 5 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS9075 1.201 ms 1 - 3 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.544 ms 0 - 95 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.537 ms 0 - 99 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® X Elite 0.684 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.572 ms 0 - 105 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS6490 3.021 ms 3 - 7 MB CPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.728 ms 0 - 4 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS9075 0.885 ms 0 - 3 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCM6690 1.935 ms 0 - 8 MB CPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.466 ms 0 - 99 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.252 ms 0 - 9 MB CPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.436 ms 0 - 99 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® X Elite 0.895 ms 1 - 1 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.487 ms 0 - 39 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8275 (Proxy) 1.691 ms 0 - 29 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8550 (Proxy) 0.754 ms 1 - 7 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA8775P 0.985 ms 1 - 30 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS9075 0.882 ms 1 - 3 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8450 (Proxy) 1.359 ms 0 - 40 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA7255P 1.691 ms 0 - 29 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA8295P 1.229 ms 0 - 25 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.354 ms 0 - 27 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.284 ms 1 - 31 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® X Elite 0.604 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.336 ms 0 - 31 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS6490 1.172 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.083 ms 0 - 22 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.477 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® SA8775P 0.643 ms 0 - 24 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS9075 0.561 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCM6690 1.334 ms 0 - 22 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.545 ms 0 - 32 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® SA7255P 1.083 ms 0 - 22 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® SA8295P 0.838 ms 0 - 21 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.262 ms 0 - 26 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.464 ms 0 - 21 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.204 ms 0 - 25 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Gen 3 Mobile 0.494 ms 0 - 39 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8275 (Proxy) 1.706 ms 0 - 28 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8550 (Proxy) 0.76 ms 0 - 2 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA8775P 4.146 ms 0 - 30 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS9075 0.887 ms 0 - 5 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8450 (Proxy) 1.37 ms 0 - 39 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA7255P 1.706 ms 0 - 28 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA8295P 1.225 ms 0 - 25 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.366 ms 0 - 27 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.282 ms 0 - 32 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.311 ms 0 - 31 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS6490 0.803 ms 0 - 3 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.105 ms 0 - 24 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.45 ms 0 - 2 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8775P 0.636 ms 0 - 25 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS9075 0.558 ms 0 - 3 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCM6690 1.055 ms 0 - 20 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.515 ms 0 - 31 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA7255P 1.105 ms 0 - 24 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8295P 0.798 ms 0 - 20 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.27 ms 0 - 21 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.44 ms 0 - 20 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.25 ms 0 - 25 MB NPU

License

  • The license for the original implementation of Shufflenet-v2 can be found here.

References

Community

Downloads last month

-

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

Paper for qualcomm/Shufflenet-v2