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 2.42, 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 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 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® 8 Elite Gen 5 Mobile 0.423 ms 0 - 31 MB NPU
Shufflenet-v2 ONNX float Snapdragon® X2 Elite 0.423 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX float Snapdragon® X Elite 0.954 ms 2 - 2 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Gen 3 Mobile 0.51 ms 0 - 41 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS8550 (Proxy) 0.811 ms 0 - 2 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS9075 1.005 ms 1 - 3 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.432 ms 0 - 32 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.338 ms 0 - 31 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® X2 Elite 0.332 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® X Elite 0.694 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.409 ms 0 - 37 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS6490 3.522 ms 4 - 7 MB CPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.57 ms 0 - 4 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS9075 0.677 ms 0 - 3 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCM6690 2.21 ms 0 - 8 MB CPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.352 ms 0 - 27 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.439 ms 0 - 9 MB CPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.286 ms 1 - 31 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® X2 Elite 0.411 ms 1 - 1 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® X Elite 0.946 ms 1 - 1 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.509 ms 0 - 39 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8275 (Proxy) 1.743 ms 1 - 29 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8550 (Proxy) 0.787 ms 1 - 2 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA8775P 1.041 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS9075 0.886 ms 1 - 3 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8450 (Proxy) 1.362 ms 0 - 41 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA7255P 1.743 ms 1 - 29 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA8295P 1.242 ms 0 - 25 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.37 ms 1 - 28 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.211 ms 0 - 25 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® X2 Elite 0.311 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® X Elite 0.597 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.332 ms 0 - 31 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS6490 1.168 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.063 ms 0 - 22 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.471 ms 0 - 71 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® SA8775P 0.655 ms 0 - 24 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS9075 0.568 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCM6690 1.349 ms 0 - 21 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.544 ms 0 - 33 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® SA7255P 1.063 ms 0 - 22 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® SA8295P 0.839 ms 0 - 20 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.263 ms 0 - 22 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.465 ms 0 - 21 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.29 ms 0 - 31 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Gen 3 Mobile 0.507 ms 0 - 39 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8275 (Proxy) 1.778 ms 0 - 28 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8550 (Proxy) 0.792 ms 0 - 2 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA8775P 1.037 ms 0 - 30 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS9075 0.893 ms 0 - 5 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8450 (Proxy) 1.378 ms 0 - 40 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA7255P 1.778 ms 0 - 28 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA8295P 1.255 ms 0 - 25 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.371 ms 0 - 28 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.25 ms 0 - 25 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.308 ms 0 - 31 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS6490 0.894 ms 0 - 3 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.031 ms 0 - 22 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.451 ms 0 - 2 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8775P 0.643 ms 0 - 24 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS9075 0.587 ms 0 - 3 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCM6690 1.072 ms 0 - 21 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.513 ms 0 - 31 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA7255P 1.031 ms 0 - 22 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8295P 0.787 ms 0 - 20 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.267 ms 0 - 22 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.44 ms 0 - 21 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