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 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.25.0 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a8 Universal QAIRT 2.45 Download
TFLITE float Universal QAIRT 2.45 Download
TFLITE w8a8 Universal QAIRT 2.45 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® X2 Elite 0.435 ms 180 - 180 MB NPU
Shufflenet-v2 ONNX float Snapdragon® X Elite 0.843 ms 178 - 178 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Gen 3 Mobile 0.519 ms 0 - 29 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Gen 1 Mobile 0.962 ms 1 - 36 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS8550 (Proxy) 0.825 ms 0 - 7 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS8450 0.962 ms 1 - 36 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Elite Mobile 0.447 ms 0 - 27 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.437 ms 0 - 24 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS9075 1.002 ms 0 - 48 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS8750 0.447 ms 0 - 27 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS7181 0.843 ms 178 - 178 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® X2 Elite 0.328 ms 213 - 213 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® X Elite 0.577 ms 177 - 177 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.395 ms 0 - 29 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.639 ms 0 - 30 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS6490 1.108 ms 0 - 47 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.579 ms 0 - 5 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS8450 0.639 ms 0 - 30 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.341 ms 0 - 27 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.526 ms 0 - 26 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCM6690 1.223 ms 0 - 26 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS9075 0.692 ms 0 - 47 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite Mobile 0.355 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS7790 0.526 ms 0 - 26 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS8750 0.355 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS7181 0.577 ms 177 - 177 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® X2 Elite 0.395 ms 1 - 1 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® X Elite 0.93 ms 1 - 1 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.513 ms 0 - 38 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.349 ms 0 - 44 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8275 1.735 ms 1 - 27 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8550 (Proxy) 0.788 ms 0 - 8 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8450 1.349 ms 0 - 44 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite Mobile 0.363 ms 0 - 26 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA8295P 1.239 ms 0 - 24 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.277 ms 1 - 27 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA7255P 1.735 ms 1 - 27 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS9075 0.882 ms 3 - 5 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8750 0.363 ms 0 - 26 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS7181 0.93 ms 1 - 1 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® X2 Elite 0.304 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® X Elite 0.586 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.335 ms 0 - 32 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.543 ms 0 - 39 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS6490 1.144 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8275 1.081 ms 0 - 24 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.47 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8450 0.543 ms 0 - 39 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.213 ms 0 - 25 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.461 ms 0 - 23 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCM6690 1.349 ms 0 - 23 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS9075 0.563 ms 2 - 4 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® SA7255P 1.081 ms 0 - 24 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.263 ms 0 - 23 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® SA8295P 0.834 ms 0 - 22 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS7790 0.461 ms 0 - 23 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8750 0.263 ms 0 - 23 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS7181 0.586 ms 0 - 0 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Gen 3 Mobile 0.498 ms 0 - 38 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Gen 1 Mobile 1.361 ms 0 - 39 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8275 1.723 ms 0 - 27 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8550 (Proxy) 0.779 ms 0 - 2 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA8775P 1.977 ms 0 - 24 MB CPU
Shufflenet-v2 TFLITE float Qualcomm® SA8650P 1.977 ms 0 - 24 MB CPU
Shufflenet-v2 TFLITE float Qualcomm® SA8255P 1.977 ms 0 - 24 MB CPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8450 1.361 ms 0 - 39 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite Mobile 0.368 ms 0 - 25 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA8295P 1.243 ms 0 - 24 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.284 ms 0 - 27 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA7255P 1.723 ms 0 - 27 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS9075 0.892 ms 0 - 5 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8750 0.368 ms 0 - 25 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.315 ms 0 - 32 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.512 ms 0 - 38 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS6490 0.815 ms 0 - 4 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8275 1.032 ms 0 - 23 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.455 ms 0 - 2 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8775P 1.918 ms 0 - 24 MB CPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8650P 1.918 ms 0 - 24 MB CPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8255P 1.918 ms 0 - 24 MB CPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8450 0.512 ms 0 - 38 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.259 ms 0 - 23 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.442 ms 0 - 22 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCM6690 1.072 ms 0 - 23 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS9075 0.558 ms 0 - 3 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA7255P 1.032 ms 0 - 23 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.271 ms 0 - 23 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8295P 0.808 ms 0 - 21 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS7790 0.442 ms 0 - 22 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8750 0.271 ms 0 - 23 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