| --- |
| 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](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/centerpoint) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary). |
|
|
| Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) 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](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.49.1/centerpoint-qnn_dlc-float.zip) |
| | TFLITE | float | Universal | TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centerpoint/releases/v0.49.1/centerpoint-tflite-float.zip) |
| |
| For more device-specific assets and performance metrics, visit **[CenterPoint on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/centerpoint)**. |
| |
| |
| ### Option 2: Export with Custom Configurations |
| |
| Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/centerpoint) 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](https://github.com/qualcomm/ai-hub-models/blob/main/qai_hub_models/models/centerpoint) 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® 8 Elite Gen 5 Mobile | 168.806 ms | 2 - 443 MB | NPU |
| | CenterPoint | QNN_DLC | float | Snapdragon® X2 Elite | 292.794 ms | 2 - 2 MB | NPU |
| | CenterPoint | QNN_DLC | float | Snapdragon® X Elite | 312.248 ms | 2 - 2 MB | NPU |
| | CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 240.53 ms | 0 - 753 MB | NPU |
| | CenterPoint | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 909.559 ms | 1 - 452 MB | NPU |
| | CenterPoint | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 317.529 ms | 2 - 5 MB | NPU |
| | CenterPoint | QNN_DLC | float | Qualcomm® QCS9075 | 396.618 ms | 2 - 11 MB | NPU |
| | CenterPoint | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 516.508 ms | 2 - 1070 MB | NPU |
| | CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 201.55 ms | 0 - 448 MB | NPU |
| | CenterPoint | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2561.328 ms | 2582 - 2592 MB | CPU |
| | CenterPoint | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4070.789 ms | 2619 - 2628 MB | CPU |
| | CenterPoint | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 6335.211 ms | 2597 - 2605 MB | CPU |
| | CenterPoint | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4776.619 ms | 2619 - 2622 MB | CPU |
| | CenterPoint | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5590.249 ms | 2591 - 2600 MB | CPU |
| | CenterPoint | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2992.93 ms | 2594 - 2606 MB | CPU |
| |
| ## License |
| * The license for the original implementation of CenterPoint can be found |
| [here](https://github.com/tianweiy/CenterPoint/blob/master/LICENSE). |
| |
| |
| |
| ## Community |
| * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI. |
| * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com). |
| |
