---
title: CenterNet-2D
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/CenterNet-2D"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/CenterNet-2D.md"
repository: Qualcomm-AI-Hub/CenterNet-2D
last_updated: 2026-10-16
license: mit
downloads: 0
stars: 0
tags:
  - android
---

# CenterNet-2D

> CenterNet-2D - Qualcomm-AI-Hub 在 ModelScope 开源的模型。CenterNet-2D: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/CenterNet-2D 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可。

- **Repository**: Qualcomm-AI-Hub/CenterNet-2D
- **License**: mit
- **Tags**: android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/CenterNet-2D

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/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/qualcomm/ai-hub-models-cn/blob/main/src/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.cn) 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® X2 Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip)
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs8275.zip)
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_qcs8275.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_sa8775p.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_qcs9075.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_sa7255p.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_sa8295p.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_2d/releases/v0.62.1/centernet_2d-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)

For more device-specific assets and performance metrics, visit **[CenterNet-2D on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/centernet_2d)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/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/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/centernet_2d) for usage instructions.

## Model Details

**Model Type:** Model_use_case.object_detection

**Model Stats:**
- Input resolution: 1 x 3 x 512 x 512
- Model checkpoint: ctdet_coco_dla_2x.pth
- Model size: 37.6 MB
- Number of parameters: 20.2M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 159.352 ms | 36 - 36 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 295.289 ms | 52 - 52 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 196.784 ms | 18 - 24 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 411.124 ms | 15 - 29 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 248.693 ms | 6 - 13 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 305.575 ms | 0 - 54 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 411.124 ms | 15 - 29 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 278.479 ms | 8 - 14 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 295.289 ms | 52 - 52 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 173.164 ms | 12 - 23 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 173.164 ms | 12 - 23 MB | NPU
| CenterNet-2D | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 166.345 ms | 16 - 23 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 160.141 ms | 3 - 3 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 293.652 ms | 3 - 3 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 196.257 ms | 3 - 11 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | 419.893 ms | 3 - 13 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | 248.847 ms | 3 - 14 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 297.992 ms | 3 - 5 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 279.954 ms | 1 - 10 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 279.954 ms | 1 - 10 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 279.954 ms | 1 - 10 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 | 419.893 ms | 3 - 13 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 277.677 ms | 3 - 13 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 293.652 ms | 3 - 3 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 173.153 ms | 0 - 15 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 477.316 ms | 0 - 10 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 355.308 ms | 0 - 6 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | 173.153 ms | 0 - 15 MB | NPU
| CenterNet-2D | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 165.649 ms | 3 - 11 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
* For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).