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 2.45, ONNX Runtime 1.27.1 Download
ONNX w8a16 Universal QAIRT 2.45, ONNX Runtime 1.27.1 Download
QNN_DLC float Universal QAIRT 2.45 Download
QNN_DLC w8a16 Universal QAIRT 2.45 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:

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

Performance Summary

Model Runtime Precision Chipset Inference Time (ms) Peak Memory Range (MB) Primary Compute Unit
RangeNet-Plus-Plus ONNX float Snapdragon® X2 Elite 50.551 ms 35 - 35 MB NPU
RangeNet-Plus-Plus ONNX float Snapdragon® X Elite 100.032 ms 101 - 101 MB NPU
RangeNet-Plus-Plus ONNX float Snapdragon® 8 Gen 3 Mobile 78.513 ms 0 - 461 MB NPU
RangeNet-Plus-Plus ONNX float Snapdragon® 8 Gen 1 Mobile 214.828 ms 1 - 524 MB NPU
RangeNet-Plus-Plus ONNX float Qualcomm® Dragonwing™ IQ-8275 178.228 ms 21 - 27 MB NPU
RangeNet-Plus-Plus ONNX float Qualcomm® Dragonwing™ QCS8550 (Proxy) 107.424 ms 0 - 122 MB NPU
RangeNet-Plus-Plus ONNX float Qualcomm® QCS8450 214.828 ms 1 - 524 MB NPU
RangeNet-Plus-Plus ONNX float Qualcomm® Dragonwing™ IQ-9075 153.128 ms 21 - 26 MB NPU
RangeNet-Plus-Plus ONNX float Qualcomm® Dragonwing™ IQ-X7181 100.032 ms 101 - 101 MB NPU
RangeNet-Plus-Plus ONNX float Qualcomm® Dragonwing™ Q-8750 59.999 ms 24 - 349 MB NPU
RangeNet-Plus-Plus ONNX float Snapdragon® 8 Elite Mobile 59.999 ms 24 - 349 MB NPU
RangeNet-Plus-Plus ONNX float Snapdragon® 8 Elite Gen 5 Mobile 42.77 ms 23 - 372 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Snapdragon® X2 Elite 37.628 ms 18 - 18 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Snapdragon® X Elite 65.688 ms 52 - 52 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Snapdragon® 8 Gen 3 Mobile 51.277 ms 0 - 473 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Snapdragon® 8 Gen 1 Mobile 108.081 ms 0 - 583 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Qualcomm® Dragonwing™ QCS6490 426.544 ms 24 - 28 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Qualcomm® Dragonwing™ IQ-8275 70.509 ms 10 - 15 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 67.587 ms 0 - 58 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Qualcomm® QCS8450 108.081 ms 0 - 583 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Qualcomm® Dragonwing™ IQ-9075 64.66 ms 14 - 18 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Qualcomm® Dragonwing™ IQ-X7181 65.688 ms 52 - 52 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Qualcomm® Dragonwing™ Q-6690 1526.679 ms 0 - 794 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Qualcomm® Dragonwing™ Q-7790 134.536 ms 31 - 556 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Qualcomm® Dragonwing™ Q-8750 44.565 ms 12 - 357 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Snapdragon® 8 Elite Mobile 44.565 ms 12 - 357 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Snapdragon® 8 Elite Gen 5 Mobile 32.089 ms 11 - 361 MB NPU
RangeNet-Plus-Plus ONNX w8a16 Snapdragon® 7 Gen 4 Mobile 134.536 ms 31 - 556 MB NPU
RangeNet-Plus-Plus QNN_DLC float Snapdragon® X2 Elite 50.097 ms 3 - 3 MB NPU
RangeNet-Plus-Plus QNN_DLC float Snapdragon® X Elite 100.142 ms 3 - 3 MB NPU
RangeNet-Plus-Plus QNN_DLC float Snapdragon® 8 Gen 3 Mobile 76.856 ms 0 - 452 MB NPU
RangeNet-Plus-Plus QNN_DLC float Snapdragon® 8 Gen 1 Mobile 207.61 ms 2 - 447 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 177.248 ms 3 - 17 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® Dragonwing™ IQ-8275 593.131 ms 2 - 334 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® Dragonwing™ QCS8550 (Proxy) 103.481 ms 3 - 35 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® SA8775P 152.813 ms 1 - 333 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® SA8650P 152.813 ms 1 - 333 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® SA8255P 152.813 ms 1 - 333 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® QCS8450 207.61 ms 2 - 447 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® Dragonwing™ IQ-9075 151.952 ms 5 - 19 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® Dragonwing™ IQ-X7181 100.142 ms 3 - 3 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® Dragonwing™ Q-8750 60.213 ms 0 - 317 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® SA7255P 593.131 ms 2 - 334 MB NPU
RangeNet-Plus-Plus QNN_DLC float Qualcomm® SA8295P 169.453 ms 0 - 327 MB NPU
RangeNet-Plus-Plus QNN_DLC float Snapdragon® 8 Elite Mobile 60.213 ms 0 - 317 MB NPU
RangeNet-Plus-Plus QNN_DLC float Snapdragon® 8 Elite Gen 5 Mobile 43.759 ms 3 - 347 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Snapdragon® X2 Elite 36.357 ms 1 - 1 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Snapdragon® X Elite 66.181 ms 1 - 1 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Snapdragon® 8 Gen 3 Mobile 52.601 ms 1 - 464 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Snapdragon® 8 Gen 1 Mobile 111.091 ms 1 - 571 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS6490 420.911 ms 3 - 11 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 68.519 ms 1 - 10 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-8275 193.454 ms 2 - 326 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® Dragonwing™ QCS8550 (Proxy) 66.991 ms 1 - 4 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® SA8775P 62.447 ms 1 - 326 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® SA8650P 62.447 ms 1 - 326 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® SA8255P 62.447 ms 1 - 326 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® QCS8450 111.091 ms 1 - 571 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-9075 62.798 ms 1 - 9 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® Dragonwing™ IQ-X7181 66.181 ms 1 - 1 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-6690 1617.23 ms 4 - 787 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-7790 130.37 ms 1 - 513 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® Dragonwing™ Q-8750 44.649 ms 1 - 337 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® SA7255P 193.454 ms 2 - 326 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Qualcomm® SA8295P 107.303 ms 2 - 431 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Snapdragon® 8 Elite Mobile 44.649 ms 1 - 337 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Snapdragon® 8 Elite Gen 5 Mobile 31.869 ms 1 - 342 MB NPU
RangeNet-Plus-Plus QNN_DLC w8a16 Snapdragon® 7 Gen 4 Mobile 130.37 ms 1 - 513 MB NPU
RangeNet-Plus-Plus TFLITE float Snapdragon® 8 Gen 3 Mobile 78.572 ms 12 - 521 MB NPU
RangeNet-Plus-Plus TFLITE float Snapdragon® 8 Gen 1 Mobile 220.596 ms 13 - 512 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® Dragonwing™ IQ-8275 178.769 ms 13 - 133 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® Dragonwing™ IQ-8275 593.569 ms 13 - 322 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® Dragonwing™ QCS8550 (Proxy) 112.891 ms 5 - 392 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA8775P 153.692 ms 13 - 323 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA8650P 153.692 ms 13 - 323 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA8255P 153.692 ms 13 - 323 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® QCS8450 220.596 ms 13 - 512 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® Dragonwing™ IQ-9075 153.606 ms 12 - 131 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® Dragonwing™ Q-8750 60.491 ms 12 - 311 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA7255P 593.569 ms 13 - 322 MB NPU
RangeNet-Plus-Plus TFLITE float Qualcomm® SA8295P 170.634 ms 13 - 315 MB NPU
RangeNet-Plus-Plus TFLITE float Snapdragon® 8 Elite Mobile 60.491 ms 12 - 311 MB NPU
RangeNet-Plus-Plus TFLITE float Snapdragon® 8 Elite Gen 5 Mobile 43.727 ms 12 - 332 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