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 | 842.229 ms | 5 - 5 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® X Elite | 1492.037 ms | 55 - 55 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1132.491 ms | 4 - 17 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1781.87 ms | 3 - 19 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 1413.172 ms | 1 - 7 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1529.958 ms | 0 - 55 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® QCS8450 | 1781.87 ms | 3 - 19 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 1480.609 ms | 0 - 6 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1492.037 ms | 55 - 55 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1023.529 ms | 2 - 14 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 1023.529 ms | 2 - 14 MB | NPU |
| CenterNet-3D | PRECOMPILED_QNN_ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 907.835 ms | 2 - 13 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X2 Elite | 839.532 ms | 3 - 3 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® X Elite | 1502.347 ms | 3 - 3 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 3 Mobile | 1131.796 ms | 3 - 10 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Gen 1 Mobile | 1769.672 ms | 3 - 13 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 1413.794 ms | 3 - 9 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-8275 | 2418.976 ms | 2 - 11 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 1523.264 ms | 3 - 5 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8775P | 1502.403 ms | 1 - 10 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8650P | 1502.403 ms | 1 - 10 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8255P | 1502.403 ms | 1 - 10 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® QCS8450 | 1769.672 ms | 3 - 13 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-9075 | 2251.142 ms | 3 - 8 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ IQ-X7181 | 1502.347 ms | 3 - 3 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® Dragonwing™ Q-8750 | 1023.599 ms | 3 - 16 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA7255P | 2418.976 ms | 2 - 11 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Qualcomm® SA8295P | 1427.539 ms | 1 - 6 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Mobile | 1023.599 ms | 3 - 16 MB | NPU |
| CenterNet-3D | QNN_CONTEXT_BINARY | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 907.968 ms | 2 - 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