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 2.45, 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 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 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® X2 Elite 0.907 ms 2 - 2 MB NPU
RegNet ONNX float Snapdragon® X Elite 1.765 ms 40 - 40 MB NPU
RegNet ONNX float Snapdragon® 8 Gen 3 Mobile 1.216 ms 0 - 129 MB NPU
RegNet ONNX float Snapdragon® 8 Gen 1 Mobile 2.747 ms 0 - 116 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ IQ-8275 3.027 ms 0 - 4 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 1.732 ms 0 - 56 MB NPU
RegNet ONNX float Qualcomm® QCS8450 2.747 ms 0 - 116 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ IQ-9075 2.817 ms 1 - 4 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ IQ-X7181 1.765 ms 40 - 40 MB NPU
RegNet ONNX float Qualcomm® Dragonwing™ Q-8750 0.998 ms 0 - 75 MB NPU
RegNet ONNX float Snapdragon® 8 Elite Mobile 0.998 ms 0 - 75 MB NPU
RegNet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.833 ms 0 - 77 MB NPU
RegNet ONNX w8a8 Snapdragon® X2 Elite 0.53 ms 1 - 1 MB NPU
RegNet ONNX w8a8 Snapdragon® X Elite 0.937 ms 21 - 21 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.657 ms 0 - 136 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 1.296 ms 0 - 135 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ QCS6490 3.942 ms 0 - 3 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-8275 1.019 ms 0 - 4 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.899 ms 0 - 62 MB NPU
RegNet ONNX w8a8 Qualcomm® QCS8450 1.296 ms 0 - 135 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-9075 1.173 ms 0 - 3 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ IQ-X7181 0.937 ms 21 - 21 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ Q-6690 7.235 ms 0 - 204 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ Q-7790 1.151 ms 0 - 87 MB NPU
RegNet ONNX w8a8 Qualcomm® Dragonwing™ Q-8750 0.549 ms 0 - 88 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Elite Mobile 0.549 ms 0 - 88 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.512 ms 0 - 89 MB NPU
RegNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 1.151 ms 0 - 87 MB NPU
RegNet QNN_DLC float Snapdragon® X2 Elite 1.233 ms 1 - 1 MB NPU
RegNet QNN_DLC float Snapdragon® X Elite 2.249 ms 1 - 1 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.413 ms 0 - 124 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Gen 1 Mobile 3.507 ms 0 - 116 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 3.181 ms 1 - 4 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.043 ms 1 - 5 MB NPU
RegNet QNN_DLC float Qualcomm® SA8775P 3.285 ms 1 - 74 MB NPU
RegNet QNN_DLC float Qualcomm® SA8650P 3.285 ms 1 - 74 MB NPU
RegNet QNN_DLC float Qualcomm® SA8255P 3.285 ms 1 - 74 MB NPU
RegNet QNN_DLC float Qualcomm® QCS8450 3.507 ms 0 - 116 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 3.057 ms 1 - 3 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 2.249 ms 1 - 1 MB NPU
RegNet QNN_DLC float Qualcomm® Dragonwing™ Q-8750 1.115 ms 1 - 76 MB NPU
RegNet QNN_DLC float Qualcomm® SA7255P 9.865 ms 1 - 71 MB NPU
RegNet QNN_DLC float Qualcomm® SA8295P 3.451 ms 0 - 61 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Elite Mobile 1.115 ms 1 - 76 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.903 ms 1 - 77 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.564 ms 0 - 0 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® X Elite 1.051 ms 0 - 0 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.632 ms 0 - 111 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 1.317 ms 0 - 112 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS6490 4.082 ms 0 - 2 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-8275 0.985 ms 0 - 3 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.867 ms 0 - 35 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA8775P 1.284 ms 0 - 82 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA8650P 1.284 ms 0 - 82 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA8255P 1.284 ms 0 - 82 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® QCS8450 1.317 ms 0 - 112 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-9075 1.127 ms 0 - 2 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ IQ-X7181 1.051 ms 0 - 0 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-6690 7.132 ms 0 - 199 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-7790 1.15 ms 0 - 79 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® Dragonwing™ Q-8750 0.488 ms 0 - 80 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA7255P 2.258 ms 0 - 80 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA8295P 1.616 ms 0 - 78 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.488 ms 0 - 80 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.44 ms 0 - 84 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.15 ms 0 - 79 MB NPU
RegNet TFLITE float Snapdragon® 8 Gen 3 Mobile 1.408 ms 0 - 151 MB NPU
RegNet TFLITE float Snapdragon® 8 Gen 1 Mobile 3.47 ms 0 - 140 MB NPU
RegNet TFLITE float Qualcomm® Dragonwing™ IQ-8275 3.179 ms 0 - 42 MB NPU
RegNet TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 2.052 ms 0 - 2 MB NPU
RegNet TFLITE float Qualcomm® SA8775P 3.278 ms 0 - 91 MB NPU
RegNet TFLITE float Qualcomm® SA8650P 3.278 ms 0 - 91 MB NPU
RegNet TFLITE float Qualcomm® SA8255P 3.278 ms 0 - 91 MB NPU
RegNet TFLITE float Qualcomm® QCS8450 3.47 ms 0 - 140 MB NPU
RegNet TFLITE float Qualcomm® Dragonwing™ IQ-9075 3.048 ms 0 - 42 MB NPU
RegNet TFLITE float Qualcomm® Dragonwing™ Q-8750 1.105 ms 0 - 83 MB NPU
RegNet TFLITE float Qualcomm® SA7255P 9.865 ms 0 - 89 MB NPU
RegNet TFLITE float Qualcomm® SA8295P 3.454 ms 0 - 72 MB NPU
RegNet TFLITE float Snapdragon® 8 Elite Mobile 1.105 ms 0 - 83 MB NPU
RegNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.898 ms 0 - 87 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.524 ms 0 - 118 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 1.118 ms 0 - 109 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS6490 3.807 ms 0 - 21 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-8275 0.819 ms 0 - 23 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ QCS8550 (Proxy) 0.708 ms 0 - 2 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8775P 1.115 ms 0 - 79 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8650P 1.115 ms 0 - 79 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8255P 1.115 ms 0 - 79 MB NPU
RegNet TFLITE w8a8 Qualcomm® QCS8450 1.118 ms 0 - 109 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ IQ-9075 0.929 ms 0 - 22 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-6690 6.632 ms 0 - 190 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-7790 0.984 ms 0 - 72 MB NPU
RegNet TFLITE w8a8 Qualcomm® Dragonwing™ Q-8750 0.422 ms 0 - 70 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA7255P 1.972 ms 0 - 75 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8295P 1.452 ms 0 - 72 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.422 ms 0 - 70 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.397 ms 0 - 77 MB NPU
RegNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.984 ms 0 - 72 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