--- library_name: pytorch license: other tags: - android pipeline_tag: object-detection --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/web-assets/model_demo.png) # CenterNet-2D: Optimized for Qualcomm Devices CenterNet-2D is machine learning model that detects objects by finding their center points. This is based on the implementation of CenterNet-2D found [here](https://github.com/xingyizhou/CenterNet). 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/centernet_2d) 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 | |---|---|---|---|---| | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip) | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip) | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5.zip) | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8275_proxy.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8775p.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip) | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_sa7255p.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_sa8295p.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs9075.zip) | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/centernet_2d/releases/v0.46.0/centernet_2d-qnn_context_binary-float-qualcomm_qcs8450_proxy.zip) For more device-specific assets and performance metrics, visit **[CenterNet-2D on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/centernet_2d)**. ### 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/centernet_2d) 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-2D on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/centernet_2d) for usage instructions. ## Model Details **Model Type:** Model_use_case.object_detection **Model Stats:** - Model checkpoint: ctdet_coco_dla_2x.pth - Input resolution: 1 x 3 x 512 x 512 - Number of parameters: 20.2M - Model size: 37.6 MB ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 382.325 ms | 56 - 56 MB | NPU | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 300.016 ms | 20 - 32 MB | NPU | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8550 (Proxy) | 396.256 ms | 0 - 62 MB | NPU | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS9075 | 395.818 ms | 9 - 14 MB | NPU | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 290.376 ms | 14 - 26 MB | NPU | CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 286.62 ms | 17 - 28 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 453.824 ms | 3 - 3 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 302.668 ms | 3 - 11 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8275 (Proxy) | 571.069 ms | 0 - 9 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8550 (Proxy) | 440.566 ms | 4 - 5 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 464.476 ms | 2 - 11 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS9075 | 455.061 ms | 3 - 13 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 (Proxy) | 646.934 ms | 3 - 13 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 571.069 ms | 0 - 9 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 498.197 ms | 0 - 5 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite For Galaxy Mobile | 305.276 ms | 0 - 9 MB | NPU | CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 237.254 ms | 3 - 13 MB | NPU ## License * The license for the original implementation of CenterNet-2D can be found [here](https://github.com/xingyizhou/CenterNet/blob/master/LICENSE). ## References * [Objects as Points](https://arxiv.org/abs/1904.07850) * [Source Model Implementation](https://github.com/xingyizhou/CenterNet) ## 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).