Image Classification
PyTorch
android

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 2.51, ONNX Runtime 1.30.0 Download
ONNX w8a16 Universal QAIRT 2.51, ONNX Runtime 1.30.0 Download
ONNX w8a8 Universal QAIRT 2.51, ONNX Runtime 1.30.0 Download
QNN_DLC float Universal QAIRT 2.51 Download
QNN_DLC w8a16 Universal QAIRT 2.51 Download
QNN_DLC w8a8 Universal QAIRT 2.51 Download
TFLITE float Universal QAIRT 2.51 Download
TFLITE w8a8 Universal QAIRT 2.51 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:

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

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 For Galaxy Mobile 0.404 ms 0 - 33 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.439 ms 0 - 32 MB NPU
Shufflenet-v2 ONNX float Snapdragon® X2 Elite 0.396 ms 2 - 2 MB NPU
Shufflenet-v2 ONNX float Snapdragon® X Elite 0.829 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Gen 3 Mobile 0.529 ms 0 - 44 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Gen 1 Mobile 0.965 ms 1 - 50 MB NPU
Shufflenet-v2 ONNX float Qualcomm® Dragonwing™ IQ-8275 0.742 ms 0 - 5 MB NPU
Shufflenet-v2 ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.811 ms 1 - 2 MB NPU
Shufflenet-v2 ONNX float Qualcomm® QCS8450 0.965 ms 1 - 50 MB NPU
Shufflenet-v2 ONNX float Qualcomm® Dragonwing™ IQ-9075 0.888 ms 1 - 4 MB NPU
Shufflenet-v2 ONNX float Qualcomm® Dragonwing™ IQ-X7181 0.829 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX float Qualcomm® Dragonwing™ Q-8750 0.439 ms 0 - 32 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.391 ms 1 - 32 MB NPU
Shufflenet-v2 ONNX float Snapdragon® 8 Elite Gen 6 Mobile 0.44 ms 1 - 32 MB NPU
Shufflenet-v2 ONNX w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.395 ms 0 - 36 MB NPU
Shufflenet-v2 ONNX w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.41 ms 0 - 38 MB NPU
Shufflenet-v2 ONNX w8a16 Snapdragon® X2 Elite 0.389 ms 1 - 1 MB NPU
Shufflenet-v2 ONNX w8a16 Snapdragon® X Elite 0.834 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 0.527 ms 0 - 45 MB NPU
Shufflenet-v2 ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 0.87 ms 0 - 50 MB NPU
Shufflenet-v2 ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 1.503 ms 0 - 3 MB NPU
Shufflenet-v2 ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 0.73 ms 0 - 4 MB NPU
Shufflenet-v2 ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.809 ms 0 - 3 MB NPU
Shufflenet-v2 ONNX w8a16 Qualcomm® QCS8450 0.87 ms 0 - 50 MB NPU
Shufflenet-v2 ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 0.848 ms 0 - 4 MB NPU
Shufflenet-v2 ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 0.834 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 2.025 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 0.805 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 0.41 ms 0 - 38 MB NPU
Shufflenet-v2 ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 0.805 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.342 ms 0 - 36 MB NPU
Shufflenet-v2 ONNX w8a16 Snapdragon® 8 Elite Gen 6 Mobile 0.418 ms 0 - 36 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.36 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.368 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® X2 Elite 0.344 ms 1 - 1 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® X Elite 0.603 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.408 ms 0 - 43 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.637 ms 0 - 51 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 1.073 ms 0 - 3 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 0.564 ms 0 - 4 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.594 ms 0 - 2 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® QCS8450 0.637 ms 0 - 51 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 0.639 ms 0 - 4 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.603 ms 0 - 0 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 1.194 ms 0 - 39 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 0.486 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.368 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.486 ms 0 - 35 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.313 ms 0 - 36 MB NPU
Shufflenet-v2 ONNX w8a8 Snapdragon® 8 Elite Gen 6 Mobile 0.339 ms 0 - 35 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.432 ms 1 - 38 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.485 ms 1 - 33 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® X2 Elite 0.546 ms 1 - 1 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® X Elite 1.076 ms 1 - 1 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.505 ms 0 - 42 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Gen 1 Mobile 1.329 ms 1 - 51 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 0.833 ms 1 - 4 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.94 ms 1 - 2 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA8650P 1.009 ms 1 - 32 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA8255P 1.009 ms 1 - 32 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® QCS8450 1.329 ms 1 - 51 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 1.028 ms 1 - 3 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 1.076 ms 1 - 1 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® Dragonwing™ Q-8750 0.485 ms 1 - 33 MB NPU
Shufflenet-v2 QNN_DLC float Qualcomm® SA8295P 1.346 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.416 ms 0 - 32 MB NPU
Shufflenet-v2 QNN_DLC float Snapdragon® 8 Elite Gen 6 Mobile 0.463 ms 0 - 31 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.461 ms 0 - 31 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Snapdragon® 8 Elite For Galaxy Mobile 0.523 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Snapdragon® X2 Elite 0.582 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Snapdragon® X Elite 1.217 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 0.518 ms 0 - 37 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 1.157 ms 0 - 46 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 2.224 ms 0 - 3 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 0.937 ms 0 - 4 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.055 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® SA8650P 0.922 ms 0 - 26 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® SA8255P 0.922 ms 0 - 26 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® QCS8450 1.157 ms 0 - 46 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 1.089 ms 0 - 3 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 1.217 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 2.813 ms 0 - 137 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 1.037 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 0.523 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Qualcomm® SA8295P 1.372 ms 0 - 29 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 1.037 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.436 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a16 Snapdragon® 8 Elite Gen 6 Mobile 0.602 ms 0 - 31 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.279 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.299 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® X2 Elite 0.373 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® X Elite 0.676 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.34 ms 0 - 37 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.608 ms 0 - 46 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 1.239 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.519 ms 0 - 3 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.563 ms 0 - 2 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® QCS8450 0.608 ms 0 - 46 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 0.581 ms 0 - 3 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.676 ms 0 - 0 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 1.503 ms 0 - 29 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 0.553 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.299 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Qualcomm® SA8295P 0.798 ms 0 - 29 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.553 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.238 ms 0 - 30 MB NPU
Shufflenet-v2 QNN_DLC w8a8 Snapdragon® 8 Elite Gen 6 Mobile 0.297 ms 0 - 30 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.24 ms 0 - 31 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.304 ms 0 - 35 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Gen 3 Mobile 0.508 ms 0 - 42 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Gen 1 Mobile 1.073 ms 0 - 50 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® Dragonwing™ IQ-8275 0.569 ms 0 - 7 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.613 ms 0 - 2 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA8650P 1.02 ms 0 - 33 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA8255P 1.02 ms 0 - 33 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® QCS8450 1.073 ms 0 - 50 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® Dragonwing™ IQ-9075 0.683 ms 0 - 6 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® Dragonwing™ Q-8750 0.304 ms 0 - 35 MB NPU
Shufflenet-v2 TFLITE float Qualcomm® SA7255P 2.645 ms 0 - 21 MB CPU
Shufflenet-v2 TFLITE float Qualcomm® SA8295P 0.964 ms 0 - 29 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.222 ms 0 - 31 MB NPU
Shufflenet-v2 TFLITE float Snapdragon® 8 Elite Gen 6 Mobile 0.293 ms 0 - 30 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.255 ms 0 - 28 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.273 ms 0 - 32 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.321 ms 0 - 37 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.503 ms 0 - 44 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 0.882 ms 0 - 4 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.41 ms 0 - 5 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.459 ms 0 - 2 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8650P 0.639 ms 0 - 30 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8255P 0.639 ms 0 - 30 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® QCS8450 0.503 ms 0 - 44 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.476 ms 0 - 4 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 1.067 ms 0 - 28 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.447 ms 0 - 27 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.273 ms 0 - 32 MB NPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA7255P 2.268 ms 1 - 20 MB CPU
Shufflenet-v2 TFLITE w8a8 Qualcomm® SA8295P 0.687 ms 0 - 28 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.447 ms 0 - 27 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite Extreme Gen 6 Mobile 0.22 ms 0 - 32 MB NPU
Shufflenet-v2 TFLITE w8a8 Snapdragon® 8 Elite Gen 6 Mobile 0.242 ms 0 - 28 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
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for qualcomm/Shufflenet-v2