Objects as Points
Paper • 1904.07850 • Published
CenterNet-3D: Optimized for Qualcomm Devices
CenterNet is a machine learning model for generating a birds eye view represenation from the sensors(cameras) mounted on a vehicle.
This is based on the implementation of CenterNet-3D 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 |
|---|---|---|---|---|
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | Download |
| QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | Download |
For more device-specific assets and performance metrics, visit CenterNet-3D 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 CenterNet-3D on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.driver_assistance
Model Stats:
- Input resolution: 1 x 3 x 384 x 1280
- Model checkpoint: ddd_3dop.pth
- Model size: 79 MB
- Number of parameters: 20.6M
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X2 Elite | 840.663 ms | 5 - 5 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 1498.139 ms | 54 - 54 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1129.663 ms | 4 - 12 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1778.245 ms | 3 - 18 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 1413.596 ms | 2 - 8 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1531.273 ms | 0 - 55 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 1778.245 ms | 3 - 18 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1480.045 ms | 0 - 6 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1498.139 ms | 54 - 54 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1024.66 ms | 1 - 13 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 1024.66 ms | 1 - 13 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 908.746 ms | 2 - 13 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 839.477 ms | 3 - 3 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 1500.565 ms | 3 - 3 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1132.361 ms | 3 - 12 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1811.482 ms | 3 - 12 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 1414.005 ms | 3 - 9 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1534.179 ms | 4 - 5 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 1502.523 ms | 2 - 10 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 1502.523 ms | 2 - 10 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 1502.523 ms | 2 - 10 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8450 | 1811.482 ms | 3 - 12 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1480.173 ms | 3 - 8 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1500.565 ms | 3 - 3 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1016.755 ms | 3 - 12 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 2417.946 ms | 1 - 10 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 1425.882 ms | 1 - 6 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | 1016.755 ms | 3 - 12 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 908.708 ms | 0 - 10 MB | NPU |
License
- The license for the original implementation of CenterNet-3D can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support