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 2.42 | 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® X Elite | 309.167 ms | 2 - 2 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 242.699 ms | 0 - 1154 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 907.737 ms | 0 - 766 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 316.66 ms | 2 - 4 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS9075 | 396.848 ms | 2 - 11 MB | NPU |
| CenterPoint | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 520.224 ms | 2 - 1065 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 201.604 ms | 1 - 719 MB | NPU |
| CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 169.206 ms | 2 - 718 MB | NPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3901.025 ms | 2620 - 2628 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 6314.032 ms | 2598 - 2606 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 5031.139 ms | 2569 - 2596 MB | CPU |
| CenterPoint | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5918.276 ms | 2624 - 2634 MB | CPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3121.304 ms | 2561 - 2570 MB | CPU |
| CenterPoint | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2674.028 ms | 2583 - 2592 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.