--- library_name: pytorch license: other tags: - android pipeline_tag: keypoint-detection --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/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/quic/ai-hub-models/blob/main/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.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 | |---|---|---|---|---| | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/litehrnet/releases/v0.47.0/litehrnet-onnx-float.zip) | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/litehrnet/releases/v0.47.0/litehrnet-qnn_dlc-float.zip) | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/litehrnet/releases/v0.47.0/litehrnet-tflite-float.zip) For more device-specific assets and performance metrics, visit **[LiteHRNet on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/litehrnet)**. ### 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/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/quic/ai-hub-models/blob/main/qai_hub_models/models/litehrnet) for usage instructions. ## Model Details **Model Type:** Model_use_case.pose_estimation **Model Stats:** - Input resolution: 256x192 - Number of parameters: 1.11M - Model size (float): 4.49 MB ## Performance Summary | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |---|---|---|---|---|---|--- | LiteHRNet | ONNX | float | Snapdragon® X Elite | 5.775 ms | 5 - 5 MB | NPU | LiteHRNet | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.131 ms | 0 - 120 MB | NPU | LiteHRNet | ONNX | float | Qualcomm® QCS8550 (Proxy) | 5.183 ms | 0 - 8 MB | NPU | LiteHRNet | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.846 ms | 0 - 98 MB | NPU | LiteHRNet | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.734 ms | 1 - 99 MB | NPU | LiteHRNet | ONNX | float | Snapdragon® X2 Elite | 2.847 ms | 5 - 5 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® X Elite | 2.388 ms | 1 - 1 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 1.365 ms | 0 - 108 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 4.906 ms | 1 - 80 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 2.094 ms | 1 - 2 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® SA8775P | 2.643 ms | 1 - 82 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® QCS9075 | 2.517 ms | 3 - 5 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 2.821 ms | 0 - 104 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® SA7255P | 4.906 ms | 1 - 80 MB | NPU | LiteHRNet | QNN_DLC | float | Qualcomm® SA8295P | 3.472 ms | 0 - 78 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 1.012 ms | 0 - 82 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 0.834 ms | 1 - 84 MB | NPU | LiteHRNet | QNN_DLC | float | Snapdragon® X2 Elite | 1.245 ms | 1 - 1 MB | NPU | LiteHRNet | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 2.708 ms | 0 - 151 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 8.745 ms | 0 - 114 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 4.22 ms | 0 - 2 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® SA8775P | 5.16 ms | 0 - 116 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® QCS9075 | 5.074 ms | 0 - 10 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 5.196 ms | 0 - 138 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® SA7255P | 8.745 ms | 0 - 114 MB | NPU | LiteHRNet | TFLITE | float | Qualcomm® SA8295P | 6.394 ms | 0 - 113 MB | NPU | LiteHRNet | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.229 ms | 0 - 111 MB | NPU | LiteHRNet | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.015 ms | 0 - 121 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 * 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).