Hugging Face's logo

qualcomm
/
RegNet

Image Classification
PyTorch
backbone
android
Model card Files
xet
 Community

RegNet: Optimized for Qualcomm Devices

RegNet 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 RegNet 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 2.50, ONNX Runtime 1.30.0 Download
ONNX w8a8 Universal QAIRT 2.50, ONNX Runtime 1.30.0 Download
QNN_DLC float Universal QAIRT 2.50 Download
QNN_DLC w8a8 Universal QAIRT 2.50 Download
TFLITE float Universal QAIRT 2.50 Download
TFLITE w8a8 Universal QAIRT 2.50 Download

For more device-specific assets and performance metrics, visit RegNet 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 RegNet 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): 58.3 MB
  • Model size (w8a8): 15.4 MB
  • Number of parameters: 15.3M

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
RegNet ONNX float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.841 ms 0 - 80 MB NPU
RegNet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.989 ms 0 - 78 MB NPU
RegNet ONNX float Snapdragon® X2 Elite 0.89 ms 2 - 2 MB NPU
RegNet ONNX float Snapdragon® X Elite 1.746 ms 40 - 40 MB NPU
RegNet ONNX float Snapdragon® 8 Gen 3 Mobile 1.221 ms 0 - 130 MB NPU
RegNet ONNX float Snapdragon® 8 Gen 1 Mobile 2.566 ms 0 - 122 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ IQ-8275 3.028 ms 0 - 5 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.726 ms 1 - 99 MB NPU
RegNet ONNX float Qualcomm® QCS8450 2.566 ms 0 - 122 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ IQ-9075 2.807 ms 1 - 4 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.746 ms 40 - 40 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ Q-8750 0.989 ms 0 - 78 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.512 ms 0 - 94 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.545 ms 0 - 94 MB NPU
RegNet ONNX w8a8 Snapdragon® X2 Elite 0.44 ms 1 - 1 MB NPU
RegNet ONNX w8a8 Snapdragon® X Elite 0.896 ms 21 - 21 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.655 ms 0 - 142 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.117 ms 0 - 137 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 2.676 ms 0 - 3 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.018 ms 0 - 4 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.887 ms 0 - 31 MB NPU
RegNet ONNX w8a8 Qualcomm® QCS8450 1.117 ms 0 - 137 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.153 ms 0 - 3 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.896 ms 21 - 21 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 7.115 ms 0 - 201 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.086 ms 0 - 90 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.545 ms 0 - 94 MB NPU
RegNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.086 ms 0 - 90 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.898 ms 1 - 78 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.113 ms 1 - 74 MB NPU
RegNet QNN_DLC float Snapdragon® X2 Elite 1.201 ms 1 - 1 MB NPU
RegNet QNN_DLC float Snapdragon® X Elite 2.284 ms 1 - 1 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.408 ms 0 - 129 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 3.376 ms 0 - 122 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 3.17 ms 1 - 4 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.049 ms 1 - 2 MB NPU
RegNet QNN_DLC float Qualcomm® SA8775P 3.202 ms 1 - 78 MB NPU
RegNet QNN_DLC float Qualcomm® SA8650P 3.202 ms 1 - 78 MB NPU
RegNet QNN_DLC float Qualcomm® SA8255P 3.202 ms 1 - 78 MB NPU
RegNet QNN_DLC float Qualcomm® QCS8450 3.376 ms 0 - 122 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 3.024 ms 1 - 3 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 2.284 ms 1 - 1 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.113 ms 1 - 74 MB NPU
RegNet QNN_DLC float Qualcomm® SA7255P 9.834 ms 1 - 75 MB NPU
RegNet QNN_DLC float Qualcomm® SA8295P 3.332 ms 0 - 65 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.438 ms 0 - 84 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.478 ms 0 - 82 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.544 ms 0 - 0 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® X Elite 1.042 ms 0 - 0 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.637 ms 0 - 112 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.101 ms 0 - 116 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 2.642 ms 0 - 2 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.965 ms 0 - 3 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.871 ms 0 - 2 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® QCS8450 1.101 ms 0 - 116 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.108 ms 2 - 4 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.042 ms 0 - 0 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 7.409 ms 0 - 195 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.189 ms 0 - 83 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.478 ms 0 - 82 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA7255P 2.239 ms 0 - 84 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA8295P 1.459 ms 0 - 81 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.189 ms 0 - 83 MB NPU
RegNet TFLITE float Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.901 ms 0 - 92 MB NPU
RegNet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.103 ms 0 - 93 MB NPU
RegNet TFLITE float Snapdragon® 8 Gen 3 Mobile 1.409 ms 0 - 155 MB NPU
RegNet TFLITE float Snapdragon® 8 Gen 1 Mobile 3.306 ms 0 - 144 MB NPU
RegNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 3.168 ms 0 - 43 MB NPU
RegNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.03 ms 0 - 3 MB NPU
RegNet TFLITE float Qualcomm® QCS8450 3.306 ms 0 - 144 MB NPU
RegNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 3.056 ms 0 - 42 MB NPU
RegNet TFLITE float Qualcomm® Dragonwing™ Q-8750 1.103 ms 0 - 93 MB NPU
RegNet TFLITE float Qualcomm® SA8295P 3.334 ms 0 - 77 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 For Galaxy Mobile 0.387 ms 0 - 76 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.42 ms 0 - 76 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.512 ms 0 - 114 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.906 ms 0 - 119 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 2.427 ms 0 - 22 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.787 ms 0 - 23 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.708 ms 0 - 4 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8775P 1.087 ms 0 - 81 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8650P 1.087 ms 0 - 81 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8255P 1.087 ms 0 - 81 MB NPU
RegNet TFLITE w8a8 Qualcomm® QCS8450 0.906 ms 0 - 119 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.915 ms 0 - 22 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 6.55 ms 0 - 188 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.973 ms 0 - 77 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.42 ms 0 - 76 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8295P 1.268 ms 0 - 75 MB NPU
RegNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.973 ms 0 - 77 MB NPU

License

  • The license for the original implementation of RegNet 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/RegNet