--- title: LiteHRNet canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/LiteHRNet" md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/LiteHRNet.md" repository: Qualcomm-AI-Hub/LiteHRNet last_updated: 2026-10-16 license: apache-2.0 downloads: 0 stars: 0 tags: - android --- # LiteHRNet > LiteHRNet - Qualcomm-AI-Hub 在 ModelScope 开源的模型。LiteHRNet: Optimized for Qualcomm Devices Qualcomm-AI-Hub/LiteHRNet 是 ModelScope 魔搭社区上的机器学习模型，采用 apache-2.0 许可。 - **Repository**: Qualcomm-AI-Hub/LiteHRNet - **License**: apache-2.0 - **Tags**: android - **Downloads**: 0 - **Stars**: 0 - **Last updated**: 2026-10-16 Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/LiteHRNet --- ![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/litehrnet/web-assets/model_demo.png) # LiteHRNet: Optimized for Qualcomm Devices LiteHRNet is a machine learning model that detects human pose and returns a location and confidence for each of 17 joints. This is based on the implementation of LiteHRNet found [here](https://github.com/HRNet/Lite-HRNet). 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/litehrnet) 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 | |---|---|---|---|---| | ONNX | float | Universal | 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/litehrnet/releases/v0.62.1/litehrnet-onnx-float.zip) | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/litehrnet/releases/v0.62.1/litehrnet-qnn_dlc-float.zip) | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/litehrnet/releases/v0.62.1/litehrnet-tflite-float.zip) For more device-specific assets and performance metrics, visit **[LiteHRNet on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/litehrnet)**. ### 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/litehrnet) 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 [LiteHRNet on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/litehrnet) for usage instructions. ## Model Details **Model Type:** Model_use_case.pose_estimation **Model Stats:** - Input resolution: 256x192 - Model size (float): 4.49 MB - Number of parameters: 1.11M ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | LiteHRNet | ONNX | float | Snapdragon® X2 Elite | 2.876 ms | 2 - 2 MB | NPU | LiteHRNet | ONNX | float | Snapdragon® X Elite | 5.727 ms | 5 - 5 MB | NPU | LiteHRNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.101 ms | 0 - 121 MB | NPU | LiteHRNet | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 6.297 ms | 1 - 121 MB | NPU | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 4.485 ms | 1 - 5 MB | NPU | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 5.427 ms | 1 - 3 MB | NPU | LiteHRNet | ONNX | float | Qualcomm® QCS8450 | 6.297 ms | 1 - 121 MB | NPU | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 5.763 ms | 1 - 4 MB | NPU | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 5.727 ms | 5 - 5 MB | NPU | LiteHRNet | ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 2.887 ms | 0 - 98 MB | NPU | LiteHRNet | ONNX | float | Snapdragon® 8 Elite Mobile | 2.887 ms | 0 - 98 MB | NPU | LiteHRNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.778 ms | 1 - 99 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® X2 Elite | 1.298 ms | 1 - 1 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® X Elite | 2.458 ms | 1 - 1 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.39 ms | 0 - 103 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 2.954 ms | 0 - 101 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-8275 | 2.189 ms | 1 - 4 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 2.11 ms | 1 - 2 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® SA8775P | 2.675 ms | 0 - 80 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® SA8650P | 2.675 ms | 0 - 80 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® SA8255P | 2.675 ms | 0 - 80 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® QCS8450 | 2.954 ms | 0 - 101 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-9075 | 2.503 ms | 3 - 5 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ IQ-X7181 | 2.458 ms | 1 - 1 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® Dragonwing™ Q-8750 | 1.08 ms | 1 - 82 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® SA7255P | 5.028 ms | 1 - 78 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® SA8295P | 3.477 ms | 0 - 81 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 1.08 ms | 1 - 82 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.908 ms | 1 - 84 MB | NPU | LiteHRNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.675 ms | 0 - 147 MB | NPU | LiteHRNet | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 5.345 ms | 1 - 138 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-8275 | 4.223 ms | 1 - 12 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 4.23 ms | 0 - 3 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® SA8775P | 5.391 ms | 1 - 116 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® SA8650P | 5.391 ms | 1 - 116 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® SA8255P | 5.391 ms | 1 - 116 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® QCS8450 | 5.345 ms | 1 - 138 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ IQ-9075 | 4.906 ms | 1 - 11 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® Dragonwing™ Q-8750 | 2.254 ms | 0 - 119 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® SA7255P | 8.832 ms | 1 - 116 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® SA8295P | 6.408 ms | 1 - 113 MB | NPU | LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Mobile | 2.254 ms | 0 - 119 MB | NPU | LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.053 ms | 0 - 109 MB | NPU ## License * The license for the original implementation of LiteHRNet can be found [here](https://github.com/HRNet/Lite-HRNet/blob/hrnet/LICENSE). ## References * [Lite-HRNet: A Lightweight High-Resolution Network](https://arxiv.org/abs/2104.06403) * [Source Model Implementation](https://github.com/HRNet/Lite-HRNet) ## Community * For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).