Hugging Face's logo

qualcomm
/
RegNet-Y-800MF

Image Classification
PyTorch
android
Model card Files
xet
Community

RegNet-Y-800MF: Optimized for Qualcomm Devices

RegNet_Y_800MF is part of the RegNet family of models designed for efficient and scalable image classification. It uses a simple yet effective design space to balance performance and computational cost, making it suitable for mobile and edge devices.

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 2.37, ONNX Runtime 1.23.0 Download
ONNX w8a8 Universal QAIRT 2.37, ONNX Runtime 1.23.0 Download
QNN_DLC float Universal QAIRT 2.42 Download
QNN_DLC w8a8 Universal QAIRT 2.42 Download
TFLITE float Universal QAIRT 2.42, TFLite 2.17.0 Download
TFLITE w8a8 Universal QAIRT 2.42, TFLite 2.17.0 Download

For more device-specific assets and performance metrics, visit RegNet-Y-800MF 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-Y-800MF on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.image_classification

Model Stats:

  • Model checkpoint: regnet_y_800mf-1b27b58c.pth
  • Input resolution: 1x3x224
  • Model size: ~6.3 MB

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
RegNet-Y-800MF ONNX float Snapdragon® X Elite 1.28 ms 14 - 14 MB NPU
RegNet-Y-800MF ONNX float Snapdragon® 8 Gen 3 Mobile 0.92 ms 0 - 141 MB NPU
RegNet-Y-800MF ONNX float Qualcomm® QCS8550 (Proxy) 1.316 ms 0 - 23 MB NPU
RegNet-Y-800MF ONNX float Qualcomm® QCS9075 1.711 ms 1 - 3 MB NPU
RegNet-Y-800MF ONNX float Snapdragon® 8 Elite For Galaxy Mobile 0.718 ms 0 - 119 MB NPU
RegNet-Y-800MF ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.691 ms 0 - 119 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® X Elite 0.86 ms 7 - 7 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.688 ms 0 - 145 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS6490 15.069 ms 4 - 12 MB CPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.93 ms 0 - 114 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS9075 1.101 ms 0 - 3 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCM6690 8.409 ms 5 - 15 MB CPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.579 ms 0 - 122 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 6.27 ms 6 - 15 MB CPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.524 ms 0 - 123 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® X Elite 1.638 ms 1 - 1 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.915 ms 0 - 78 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS8275 (Proxy) 4.019 ms 1 - 53 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.381 ms 1 - 2 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® SA8775P 1.878 ms 1 - 56 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS9075 1.716 ms 1 - 3 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS8450 (Proxy) 2.22 ms 0 - 72 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® SA7255P 4.019 ms 1 - 53 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® SA8295P 2.183 ms 0 - 48 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® 8 Elite For Galaxy Mobile 0.69 ms 0 - 58 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.605 ms 1 - 57 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® X Elite 0.869 ms 0 - 0 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.492 ms 0 - 65 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS6490 1.708 ms 0 - 2 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS8275 (Proxy) 1.618 ms 0 - 46 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.689 ms 0 - 2 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® SA8775P 3.777 ms 0 - 46 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS9075 0.85 ms 0 - 2 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCM6690 2.802 ms 0 - 47 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS8450 (Proxy) 0.854 ms 0 - 67 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® SA7255P 1.618 ms 0 - 46 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® SA8295P 1.133 ms 0 - 45 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.384 ms 0 - 50 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.729 ms 0 - 46 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.308 ms 0 - 50 MB NPU
RegNet-Y-800MF TFLITE float Snapdragon® 8 Gen 3 Mobile 0.915 ms 0 - 93 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® QCS8275 (Proxy) 4.029 ms 0 - 63 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® QCS8550 (Proxy) 1.384 ms 0 - 3 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® SA8775P 7.985 ms 0 - 64 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® QCS9075 1.71 ms 0 - 17 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® QCS8450 (Proxy) 2.208 ms 0 - 78 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® SA7255P 4.029 ms 0 - 63 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® SA8295P 2.174 ms 0 - 55 MB NPU
RegNet-Y-800MF TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 0.685 ms 0 - 57 MB NPU
RegNet-Y-800MF TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.61 ms 0 - 69 MB NPU
RegNet-Y-800MF TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.369 ms 0 - 63 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS6490 1.332 ms 0 - 9 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS8275 (Proxy) 1.272 ms 0 - 48 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.513 ms 0 - 2 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® SA8775P 0.759 ms 0 - 52 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS9075 0.667 ms 0 - 9 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCM6690 2.368 ms 0 - 42 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS8450 (Proxy) 0.679 ms 0 - 72 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® SA7255P 1.272 ms 0 - 48 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® SA8295P 0.899 ms 0 - 43 MB NPU
RegNet-Y-800MF TFLITE w8a8 Snapdragon® 8 Elite For Galaxy Mobile 0.307 ms 0 - 41 MB NPU
RegNet-Y-800MF TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.555 ms 0 - 42 MB NPU
RegNet-Y-800MF TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.26 ms 0 - 51 MB NPU

License

  • The license for the original implementation of RegNet-Y-800MF can be found here.

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