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 1.27.1 | Download |
| ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| QNN_DLC | float | Universal | QAIRT 2.45 | Download |
| QNN_DLC | w8a16 | 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:
- 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® X2 Elite | 0.439 ms | 2 - 2 MB | NPU |
| Shufflenet-v2 | ONNX | float | Snapdragon® X Elite | 0.839 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 0.518 ms | 0 - 40 MB | NPU |
| Shufflenet-v2 | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 0.997 ms | 1 - 45 MB | NPU |
| Shufflenet-v2 | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 0.831 ms | 0 - 4 MB | NPU |
| Shufflenet-v2 | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.826 ms | 0 - 5 MB | NPU |
| Shufflenet-v2 | ONNX | float | Qualcomm® QCS8450 | 0.997 ms | 1 - 45 MB | NPU |
| Shufflenet-v2 | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 0.98 ms | 1 - 3 MB | NPU |
| Shufflenet-v2 | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.839 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 0.444 ms | 0 - 31 MB | NPU |
| Shufflenet-v2 | ONNX | float | Snapdragon® 8 Elite Mobile | 0.444 ms | 0 - 31 MB | NPU |
| Shufflenet-v2 | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.439 ms | 0 - 27 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Snapdragon® X2 Elite | 0.382 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 | 0.521 ms | 0 - 40 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 0.89 ms | 0 - 45 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 1.772 ms | 0 - 3 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 0.8 ms | 0 - 4 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.81 ms | 0 - 3 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Qualcomm® QCS8450 | 0.89 ms | 0 - 45 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 0.944 ms | 0 - 3 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 | 1.978 ms | 0 - 30 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 0.791 ms | 0 - 30 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.415 ms | 0 - 29 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 0.415 ms | 0 - 29 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.389 ms | 0 - 30 MB | NPU |
| Shufflenet-v2 | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.791 ms | 0 - 30 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Snapdragon® X2 Elite | 0.344 ms | 1 - 1 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Snapdragon® X Elite | 0.578 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.398 ms | 0 - 39 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.635 ms | 0 - 41 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.155 ms | 0 - 3 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.634 ms | 0 - 4 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.576 ms | 0 - 5 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Qualcomm® QCS8450 | 0.635 ms | 0 - 41 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.695 ms | 0 - 3 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.578 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1.222 ms | 0 - 30 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.521 ms | 0 - 29 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.356 ms | 0 - 29 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 0.356 ms | 0 - 29 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.345 ms | 0 - 31 MB | NPU |
| Shufflenet-v2 | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.521 ms | 0 - 29 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Snapdragon® X2 Elite | 0.388 ms | 1 - 1 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Snapdragon® X Elite | 0.915 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 | 1.353 ms | 0 - 43 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 0.773 ms | 1 - 4 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.785 ms | 1 - 16 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® SA8775P | 0.997 ms | 1 - 29 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® SA8650P | 0.997 ms | 1 - 29 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® SA8255P | 0.997 ms | 1 - 29 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® QCS8450 | 1.353 ms | 0 - 43 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 0.888 ms | 1 - 3 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 0.915 ms | 1 - 1 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 0.364 ms | 1 - 27 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® SA7255P | 1.737 ms | 1 - 27 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Qualcomm® SA8295P | 1.237 ms | 0 - 24 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 0.364 ms | 1 - 27 MB | NPU |
| Shufflenet-v2 | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.283 ms | 1 - 28 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 0.381 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Snapdragon® X Elite | 0.855 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 0.502 ms | 0 - 32 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Snapdragon® 8 Gen 1 Mobile | 0.832 ms | 0 - 38 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS6490 | 2.195 ms | 0 - 2 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 0.735 ms | 0 - 3 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.738 ms | 0 - 2 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® SA8775P | 0.922 ms | 0 - 26 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 | 0.832 ms | 0 - 38 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 0.823 ms | 0 - 2 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 0.855 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-6690 | 2.222 ms | 0 - 137 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-7790 | 0.733 ms | 0 - 22 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 0.343 ms | 0 - 24 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Qualcomm® SA8295P | 1.14 ms | 0 - 23 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 0.343 ms | 0 - 24 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 0.271 ms | 0 - 23 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 0.733 ms | 0 - 22 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 0.323 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Snapdragon® X Elite | 0.585 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.338 ms | 0 - 32 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.54 ms | 0 - 38 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 1.204 ms | 0 - 2 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.505 ms | 0 - 3 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.471 ms | 0 - 2 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® SA8775P | 0.644 ms | 0 - 26 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® SA8650P | 0.644 ms | 0 - 26 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® SA8255P | 0.644 ms | 0 - 26 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 0.54 ms | 0 - 38 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.546 ms | 0 - 2 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ IQ-X7181 | 0.585 ms | 0 - 0 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1.347 ms | 0 - 23 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.46 ms | 0 - 23 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.263 ms | 0 - 23 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® SA7255P | 1.069 ms | 0 - 25 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Qualcomm® SA8295P | 0.823 ms | 0 - 22 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 0.263 ms | 0 - 23 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.215 ms | 0 - 23 MB | NPU |
| Shufflenet-v2 | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.46 ms | 0 - 23 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 0.503 ms | 0 - 38 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 1.364 ms | 0 - 44 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 0.777 ms | 0 - 6 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.795 ms | 0 - 27 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® SA8775P | 1.023 ms | 0 - 29 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® SA8650P | 1.023 ms | 0 - 29 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® SA8255P | 1.023 ms | 0 - 29 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® QCS8450 | 1.364 ms | 0 - 44 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 0.908 ms | 0 - 6 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 0.369 ms | 0 - 25 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® SA7255P | 1.733 ms | 0 - 26 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Qualcomm® SA8295P | 1.245 ms | 0 - 24 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Snapdragon® 8 Elite Mobile | 0.369 ms | 0 - 25 MB | NPU |
| Shufflenet-v2 | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.284 ms | 0 - 27 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 0.318 ms | 0 - 32 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 0.514 ms | 0 - 38 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS6490 | 0.86 ms | 0 - 4 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-8275 | 0.523 ms | 0 - 4 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 0.458 ms | 0 - 1 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® SA8775P | 0.648 ms | 0 - 26 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® SA8650P | 0.648 ms | 0 - 26 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® SA8255P | 0.648 ms | 0 - 26 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® QCS8450 | 0.514 ms | 0 - 38 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ IQ-9075 | 0.549 ms | 0 - 4 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-6690 | 1.084 ms | 0 - 22 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-7790 | 0.443 ms | 0 - 22 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® Dragonwing™ Q-8750 | 0.273 ms | 0 - 28 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® SA7255P | 1.032 ms | 0 - 26 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Qualcomm® SA8295P | 0.798 ms | 0 - 21 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 0.273 ms | 0 - 28 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 0.251 ms | 0 - 23 MB | NPU |
| Shufflenet-v2 | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 0.443 ms | 0 - 22 MB | NPU |
License
- The license for the original implementation of Shufflenet-v2 can be found here.
References
- ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design
- Source Model Implementation
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
