Hugging Face's logo

qualcomm
/
RegNet

Image Classification
PyTorch
backbone
android
Model card Files
xet
 Community
RegNet / README.md
qaihm-bot's picture
qaihm-bot
v0.51.0
a952b02 verified
preview code
|
raw
history blame contribute delete
9.77 kB
metadata 
library_name: pytorch
license: other
tags:
  - backbone
  - android
pipeline_tag: image-classification

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 2.42, ONNX Runtime 1.24.3 Download
ONNX w8a8 Universal QAIRT 2.42, ONNX Runtime 1.24.3 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:

  • Model checkpoint: Imagenet
  • Input resolution: 224x224
  • Number of parameters: 15.3M
  • Model size (float): 58.3 MB
  • Model size (w8a8): 15.4 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
RegNet ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.834 ms 1 - 88 MB NPU
RegNet ONNX float Snapdragon® X2 Elite 0.904 ms 39 - 39 MB NPU
RegNet ONNX float Snapdragon® X Elite 1.961 ms 39 - 39 MB NPU
RegNet ONNX float Snapdragon® 8 Gen 3 Mobile 1.244 ms 0 - 137 MB NPU
RegNet ONNX float Qualcomm® QCS8550 (Proxy) 1.798 ms 0 - 4 MB NPU
RegNet ONNX float Qualcomm® QCS9075 2.852 ms 0 - 4 MB NPU
RegNet ONNX float Snapdragon® 8 Elite For Galaxy Mobile 1.0 ms 0 - 86 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.511 ms 0 - 90 MB NPU
RegNet ONNX w8a8 Snapdragon® X2 Elite 0.484 ms 20 - 20 MB NPU
RegNet ONNX w8a8 Snapdragon® X Elite 1.111 ms 20 - 20 MB NPU
RegNet ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.651 ms 0 - 135 MB NPU
RegNet ONNX w8a8 Qualcomm® QCS6490 27.965 ms 8 - 19 MB CPU
RegNet ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.931 ms 0 - 30 MB NPU
RegNet ONNX w8a8 Qualcomm® QCS9075 1.084 ms 0 - 3 MB NPU
RegNet ONNX w8a8 Qualcomm® QCM6690 18.301 ms 7 - 17 MB CPU
RegNet ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.556 ms 0 - 89 MB NPU
RegNet ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 13.811 ms 9 - 18 MB CPU
RegNet QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.896 ms 1 - 77 MB NPU
RegNet QNN_DLC float Snapdragon® X2 Elite 1.214 ms 1 - 1 MB NPU
RegNet QNN_DLC float Snapdragon® X Elite 2.275 ms 1 - 1 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Gen 3 Mobile 1.408 ms 0 - 125 MB NPU
RegNet QNN_DLC float Qualcomm® QCS8275 (Proxy) 9.827 ms 1 - 72 MB NPU
RegNet QNN_DLC float Qualcomm® QCS8550 (Proxy) 2.038 ms 1 - 2 MB NPU
RegNet QNN_DLC float Qualcomm® SA8775P 3.258 ms 1 - 74 MB NPU
RegNet QNN_DLC float Qualcomm® QCS9075 3.034 ms 1 - 3 MB NPU
RegNet QNN_DLC float Qualcomm® QCS8450 (Proxy) 3.506 ms 0 - 117 MB NPU
RegNet QNN_DLC float Qualcomm® SA7255P 9.827 ms 1 - 72 MB NPU
RegNet QNN_DLC float Qualcomm® SA8295P 3.465 ms 1 - 62 MB NPU
RegNet QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 1.114 ms 1 - 74 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.429 ms 0 - 82 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® X2 Elite 0.572 ms 0 - 0 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® X Elite 1.061 ms 0 - 0 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.632 ms 0 - 108 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® QCS6490 2.625 ms 0 - 2 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 2.265 ms 0 - 78 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.87 ms 0 - 2 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA8775P 1.28 ms 0 - 80 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® QCS9075 1.042 ms 0 - 2 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® QCM6690 7.094 ms 0 - 198 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 1.315 ms 0 - 110 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA7255P 2.265 ms 0 - 78 MB NPU
RegNet QNN_DLC w8a8 Qualcomm® SA8295P 1.587 ms 0 - 77 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.478 ms 0 - 78 MB NPU
RegNet QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 1.183 ms 0 - 79 MB NPU
RegNet TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.891 ms 0 - 93 MB NPU
RegNet TFLITE float Snapdragon® 8 Gen 3 Mobile 1.4 ms 0 - 153 MB NPU
RegNet TFLITE float Qualcomm® QCS8275 (Proxy) 9.857 ms 0 - 88 MB NPU
RegNet TFLITE float Qualcomm® QCS8550 (Proxy) 2.08 ms 0 - 3 MB NPU
RegNet TFLITE float Qualcomm® SA8775P 3.28 ms 0 - 91 MB NPU
RegNet TFLITE float Qualcomm® QCS9075 3.027 ms 0 - 42 MB NPU
RegNet TFLITE float Qualcomm® QCS8450 (Proxy) 3.477 ms 0 - 136 MB NPU
RegNet TFLITE float Qualcomm® SA7255P 9.857 ms 0 - 88 MB NPU
RegNet TFLITE float Qualcomm® SA8295P 3.472 ms 0 - 72 MB NPU
RegNet TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 1.104 ms 0 - 92 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.385 ms 0 - 79 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.515 ms 0 - 121 MB NPU
RegNet TFLITE w8a8 Qualcomm® QCS6490 2.253 ms 0 - 22 MB NPU
RegNet TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.99 ms 0 - 76 MB NPU
RegNet TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.724 ms 0 - 19 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8775P 1.108 ms 0 - 77 MB NPU
RegNet TFLITE w8a8 Qualcomm® QCS9075 0.879 ms 0 - 22 MB NPU
RegNet TFLITE w8a8 Qualcomm® QCM6690 6.623 ms 0 - 192 MB NPU
RegNet TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 1.123 ms 0 - 112 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA7255P 1.99 ms 0 - 76 MB NPU
RegNet TFLITE w8a8 Qualcomm® SA8295P 1.413 ms 0 - 72 MB NPU
RegNet TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.43 ms 0 - 76 MB NPU
RegNet TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.985 ms 0 - 73 MB NPU

License

  • The license for the original implementation of RegNet can be found here.

References

Community