Hugging Face's logo

qualcomm
/
RangeNet-Plus-Plus

Other
PyTorch
real_time
bu_auto
android
Model card Files
xet
 Community

RangeNet-Plus-Plus: Optimized for Qualcomm Devices

RangeNet-Plus-Plus (also stylized as RangeNet++) projects a LiDAR point cloud onto a 5-channel range image (depth, x, y, z, intensity) and applies a DarkNet-53 encoder with a decoder head to predict per-point semantic class labels in real time.

This is based on the implementation of RangeNet-Plus-Plus 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 1.25.0 Download
TFLITE float Universal QAIRT 2.45 Download

For more device-specific assets and performance metrics, visit RangeNet-Plus-Plus 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 RangeNet-Plus-Plus on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.driver_assistance

Model Stats:

  • Model checkpoint: darknet53_rangenet++
  • Input resolution: 64x2048
  • Input channels: 5
  • Number of output classes: 20
  • Backbone: DarkNet-53

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
RangeNet-Plus-Plus ONNX float Snapdragon® 8 Elite Gen 5 Mobile 43.811 ms 3 - 332 MB NPU
RangeNet-Plus-Plus ONNX float Snapdragon® X2 Elite 49.542 ms 165 - 165 MB NPU
RangeNet-Plus-Plus ONNX float Snapdragon® 8 Gen 3 Mobile 75.497 ms 3 - 465 MB NPU
RangeNet-Plus-Plus ONNX float Qualcomm® QCS8550 (Proxy) 100.826 ms 0 - 125 MB NPU
RangeNet-Plus-Plus ONNX float Snapdragon® 8 Elite For Galaxy Mobile 58.87 ms 1 - 328 MB NPU
RangeNet-Plus-Plus ONNX float Qualcomm® QCS9075 159.124 ms 2 - 48 MB NPU
RangeNet-Plus-Plus ONNX float Qualcomm® QCS8750 58.87 ms 1 - 328 MB NPU
RangeNet-Plus-Plus TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 44.104 ms 0 - 315 MB NPU
RangeNet-Plus-Plus TFLITE float Snapdragon® 8 Gen 3 Mobile 77.735 ms 0 - 509 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® QCS8275 596.851 ms 1 - 308 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® QCS8550 (Proxy) 98.487 ms 0 - 137 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA8775P 154.752 ms 1 - 309 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA8650P 154.752 ms 1 - 309 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA8255P 154.752 ms 1 - 309 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® QCS8450 (Proxy) 191.599 ms 0 - 497 MB NPU
RangeNet-Plus-Plus TFLITE float Snapdragon® 8 Elite For Galaxy Mobile 60.9 ms 0 - 293 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® QCS9075 168.496 ms 0 - 107 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA7255P 596.851 ms 1 - 308 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA8295P 171.982 ms 1 - 302 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® QCS8750 60.9 ms 0 - 293 MB NPU

License

  • The license for the original implementation of RangeNet-Plus-Plus can be found here.

References

Community

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
Other
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support