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 2.45, ONNX Runtime 1.25.0 Download
ONNX w8a8 Universal QAIRT 2.45, ONNX Runtime 1.25.0 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-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® X2 Elite 0.539 ms 212 - 212 MB NPU
RegNet-Y-800MF ONNX float Snapdragon® X Elite 1.132 ms 181 - 181 MB NPU
RegNet-Y-800MF ONNX float Snapdragon® 8 Gen 3 Mobile 0.708 ms 0 - 66 MB NPU
RegNet-Y-800MF ONNX float Snapdragon® 8 Gen 1 Mobile 1.458 ms 1 - 65 MB NPU
RegNet-Y-800MF ONNX float Qualcomm® QCS8550 (Proxy) 1.087 ms 0 - 32 MB NPU
RegNet-Y-800MF ONNX float Qualcomm® QCS8450 1.458 ms 1 - 65 MB NPU
RegNet-Y-800MF ONNX float Snapdragon® 8 Elite Mobile 0.56 ms 0 - 55 MB NPU
RegNet-Y-800MF ONNX float Snapdragon® 8 Elite Gen 5 Mobile 0.535 ms 1 - 51 MB NPU
RegNet-Y-800MF ONNX float Qualcomm® QCS9075 1.473 ms 1 - 46 MB NPU
RegNet-Y-800MF ONNX float Qualcomm® QCS8750 0.56 ms 0 - 55 MB NPU
RegNet-Y-800MF ONNX float Qualcomm® QCS7181 1.132 ms 181 - 181 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® X2 Elite 0.375 ms 213 - 213 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® X Elite 0.723 ms 156 - 156 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® 8 Gen 3 Mobile 0.486 ms 0 - 77 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® 8 Gen 1 Mobile 0.871 ms 0 - 74 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS6490 1.549 ms 0 - 45 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS8550 (Proxy) 0.701 ms 0 - 98 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS8450 0.871 ms 0 - 74 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.378 ms 0 - 56 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® 7 Gen 4 Mobile 0.691 ms 0 - 53 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCM6690 2.58 ms 0 - 58 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS9075 0.861 ms 0 - 53 MB NPU
RegNet-Y-800MF ONNX w8a8 Snapdragon® 8 Elite Mobile 0.429 ms 0 - 56 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS7790 0.691 ms 0 - 53 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS8750 0.429 ms 0 - 56 MB NPU
RegNet-Y-800MF ONNX w8a8 Qualcomm® QCS7181 0.723 ms 156 - 156 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® X2 Elite 0.826 ms 1 - 1 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® X Elite 1.615 ms 1 - 1 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® 8 Gen 3 Mobile 0.907 ms 0 - 75 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® 8 Gen 1 Mobile 2.223 ms 1 - 75 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS8275 4.026 ms 1 - 49 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS8550 (Proxy) 1.414 ms 0 - 12 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS8450 2.223 ms 1 - 75 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® 8 Elite Mobile 0.695 ms 1 - 52 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® SA8295P 2.122 ms 0 - 44 MB NPU
RegNet-Y-800MF QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 0.621 ms 1 - 56 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® SA7255P 4.026 ms 1 - 49 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS9075 1.696 ms 1 - 3 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS8750 0.695 ms 1 - 52 MB NPU
RegNet-Y-800MF QNN_DLC float Qualcomm® QCS7181 1.615 ms 1 - 1 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® X2 Elite 0.453 ms 0 - 0 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® X Elite 0.844 ms 0 - 0 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® 8 Gen 3 Mobile 0.483 ms 0 - 66 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® 8 Gen 1 Mobile 0.862 ms 0 - 70 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS6490 1.696 ms 0 - 2 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS8275 1.57 ms 0 - 48 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS8550 (Proxy) 0.69 ms 0 - 2 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS8450 0.862 ms 0 - 70 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.314 ms 0 - 48 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® 7 Gen 4 Mobile 0.723 ms 0 - 47 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCM6690 2.874 ms 0 - 48 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS9075 0.843 ms 0 - 2 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® SA7255P 1.57 ms 0 - 48 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Snapdragon® 8 Elite Mobile 0.38 ms 0 - 47 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® SA8295P 1.107 ms 0 - 46 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS7790 0.723 ms 0 - 47 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS8750 0.38 ms 0 - 47 MB NPU
RegNet-Y-800MF QNN_DLC w8a8 Qualcomm® QCS7181 0.844 ms 0 - 0 MB NPU
RegNet-Y-800MF TFLITE float Snapdragon® 8 Gen 3 Mobile 0.909 ms 0 - 88 MB NPU
RegNet-Y-800MF TFLITE float Snapdragon® 8 Gen 1 Mobile 2.21 ms 0 - 80 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® QCS8275 4.049 ms 0 - 59 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® QCS8550 (Proxy) 1.414 ms 0 - 7 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® SA8775P 5.722 ms 0 - 28 MB GPU
RegNet-Y-800MF TFLITE float Qualcomm® SA8650P 5.722 ms 0 - 28 MB GPU
RegNet-Y-800MF TFLITE float Qualcomm® SA8255P 5.722 ms 0 - 28 MB GPU
RegNet-Y-800MF TFLITE float Qualcomm® QCS8450 2.21 ms 0 - 80 MB NPU
RegNet-Y-800MF TFLITE float Snapdragon® 8 Elite Mobile 0.685 ms 0 - 54 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® SA8295P 2.149 ms 0 - 50 MB NPU
RegNet-Y-800MF TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 0.613 ms 0 - 59 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® SA7255P 4.049 ms 0 - 59 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® QCS9075 1.706 ms 0 - 17 MB NPU
RegNet-Y-800MF TFLITE float Qualcomm® QCS8750 0.685 ms 0 - 54 MB NPU
RegNet-Y-800MF TFLITE w8a8 Snapdragon® 8 Gen 3 Mobile 0.354 ms 0 - 66 MB NPU
RegNet-Y-800MF TFLITE w8a8 Snapdragon® 8 Gen 1 Mobile 0.671 ms 0 - 66 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS6490 1.171 ms 0 - 9 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS8275 1.257 ms 0 - 48 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS8550 (Proxy) 0.52 ms 0 - 2 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® SA8775P 6.088 ms 0 - 28 MB GPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® SA8650P 6.088 ms 0 - 28 MB GPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® SA8255P 6.088 ms 0 - 28 MB GPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS8450 0.671 ms 0 - 66 MB NPU
RegNet-Y-800MF TFLITE w8a8 Snapdragon® 8 Elite Gen 5 Mobile 0.255 ms 0 - 43 MB NPU
RegNet-Y-800MF TFLITE w8a8 Snapdragon® 7 Gen 4 Mobile 0.534 ms 0 - 43 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCM6690 2.334 ms 0 - 44 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS9075 0.67 ms 0 - 10 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® SA7255P 1.257 ms 0 - 48 MB NPU
RegNet-Y-800MF TFLITE w8a8 Snapdragon® 8 Elite Mobile 0.302 ms 0 - 43 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® SA8295P 0.919 ms 0 - 44 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS7790 0.534 ms 0 - 43 MB NPU
RegNet-Y-800MF TFLITE w8a8 Qualcomm® QCS8750 0.302 ms 0 - 43 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