library_name: pytorch
license: other
tags:
- android
pipeline_tag: other
CenterPoint: Optimized for Qualcomm Devices
CenterPoint is a LiDAR-based 3D object detection model that detects objects by predicting their centers and regressing other attributes. It is designed for high accuracy and real-time performance in autonomous driving applications.
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 |
|---|---|---|---|---|
| QNN_DLC | float | Universal | QAIRT 2.43 | Download |
| TFLITE | float | Universal | TFLite 2.17.0 | Download |
For more device-specific assets and performance metrics, visit CenterPoint 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 CenterPoint on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.driver_assistance
Model Stats:
- Model checkpoint: PointPillars
- Input resolution: 5x20x5, 5x4, 5
- Number of parameters: 21.8M
- Model size: 83.3 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| CenterPoint | QNN_DLC | float | Snapdragon® X2 Elite | 180.87 ms | 2 - 2 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® X Elite | 312.052 ms | 2 - 2 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 244.881 ms | 0 - 752 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 909.147 ms | 1 - 452 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 323.63 ms | 2 - 366 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS9075 | 397.079 ms | 2 - 11 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 510.792 ms | 1 - 1067 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 201.763 ms | 0 - 449 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 171.022 ms | 2 - 444 MB | NPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3953.577 ms | 2652 - 2660 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 6321.638 ms | 2607 - 2615 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 5057.038 ms | 2568 - 2595 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5831.27 ms | 2625 - 2635 MB | CPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3022.673 ms | 2620 - 2629 MB | CPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2542.905 ms | 2652 - 2662 MB | CPU |
License
- The license for the original implementation of CenterPoint can be found here.
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.