qualcomm
/

CenterPoint

@@ -13,7 +13,7 @@ pipeline_tag: other
 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/quic/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.
@@ -26,22 +26,22 @@ 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/v0.47.0/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/v0.47.0/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/quic/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/quic/ai-hub-models/blob/main/qai_hub_models/models/centerpoint) for usage instructions.
 ## Model Details
@@ -56,21 +56,21 @@ See our repository for [CenterPoint on GitHub](https://github.com/quic/ai-hub-mo
 ## Performance Summary
 | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
 |---|---|---|---|---|---|---
-| CenterPoint | QNN_DLC | float | Snapdragon® X Elite | 310.985 ms | 2 - 2 MB | NPU
-| CenterPoint | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 245.04 ms | 2 - 757 MB | NPU
-| CenterPoint | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 909.207 ms | 1 - 452 MB | NPU
-| CenterPoint | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 319.384 ms | 2 - 5 MB | NPU
-| CenterPoint | QNN_DLC | float | Qualcomm® QCS9075 | 396.805 ms | 2 - 11 MB | NPU
-| CenterPoint | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 514.117 ms | 2 - 1067 MB | NPU
-| CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 201.857 ms | 0 - 449 MB | NPU
-| CenterPoint | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 170.344 ms | 2 - 443 MB | NPU
-| CenterPoint | QNN_DLC | float | Snapdragon® X2 Elite | 182.704 ms | 2 - 2 MB | NPU
-| CenterPoint | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 3826.156 ms | 2622 - 2630 MB | CPU
-| CenterPoint | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 6336.958 ms | 2598 - 2606 MB | CPU
-| CenterPoint | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4687.416 ms | 2619 - 2621 MB | CPU
-| CenterPoint | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5713.929 ms | 2591 - 2601 MB | CPU
-| CenterPoint | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3014.608 ms | 2594 - 2607 MB | CPU
-| CenterPoint | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2412.777 ms | 2653 - 2663 MB | CPU
 ## License
 * The license for the original implementation of CenterPoint can be found

 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.
 | 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/v0.48.0/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/v0.48.0/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
 ## 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