--- library_name: pytorch license: other pipeline_tag: keypoint-detection tags: - quantized - android --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/hrnet_pose_quantized/web-assets/model_demo.png) # HRNetPoseQuantized: Optimized for Mobile Deployment ## Perform accurate human pose estimation HRNet performs pose estimation in high-resolution representations. This model is an implementation of HRNetPoseQuantized found [here](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/hrnet_posenet). This repository provides scripts to run HRNetPoseQuantized on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/hrnet_pose_quantized). ### Model Details - **Model Type:** Pose estimation - **Model Stats:** - Model checkpoint: hrnet_posenet_FP32_state_dict - Input resolution: 256x192 - Number of parameters: 28.5M - Model size: 109 MB | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | HRNetPoseQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.963 ms | 0 - 2 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 1.241 ms | 0 - 15 MB | INT8 | NPU | [HRNetPoseQuantized.so](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.so) | | HRNetPoseQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.708 ms | 0 - 106 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 0.895 ms | 0 - 34 MB | INT8 | NPU | [HRNetPoseQuantized.so](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.so) | | HRNetPoseQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.574 ms | 0 - 64 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 0.749 ms | 0 - 33 MB | INT8 | NPU | Use Export Script | | HRNetPoseQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | TFLITE | 3.983 ms | 0 - 68 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 5.337 ms | 0 - 8 MB | INT8 | NPU | Use Export Script | | HRNetPoseQuantized | RB5 (Proxy) | QCS8250 Proxy | TFLITE | 17.077 ms | 0 - 4 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.948 ms | 0 - 3 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 1.201 ms | 0 - 1 MB | INT8 | NPU | Use Export Script | | HRNetPoseQuantized | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.97 ms | 0 - 2 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 1.217 ms | 0 - 2 MB | INT8 | NPU | Use Export Script | | HRNetPoseQuantized | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 0.96 ms | 0 - 2 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | SA8775 (Proxy) | SA8775P Proxy | QNN | 1.209 ms | 0 - 2 MB | INT8 | NPU | Use Export Script | | HRNetPoseQuantized | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.962 ms | 0 - 4 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 1.217 ms | 0 - 1 MB | INT8 | NPU | Use Export Script | | HRNetPoseQuantized | SA8295P ADP | SA8295P | TFLITE | 1.656 ms | 0 - 63 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | SA8295P ADP | SA8295P | QNN | 2.029 ms | 0 - 5 MB | INT8 | NPU | Use Export Script | | HRNetPoseQuantized | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.174 ms | 0 - 109 MB | INT8 | NPU | [HRNetPoseQuantized.tflite](https://huggingface.co/qualcomm/HRNetPoseQuantized/blob/main/HRNetPoseQuantized.tflite) | | HRNetPoseQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 1.459 ms | 0 - 36 MB | INT8 | NPU | Use Export Script | | HRNetPoseQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 1.414 ms | 0 - 0 MB | INT8 | NPU | Use Export Script | ## Installation This model can be installed as a Python package via pip. ```bash pip install "qai-hub-models[hrnet_pose_quantized]" ``` ## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`. With this API token, you can configure your client to run models on the cloud hosted devices. ```bash qai-hub configure --api_token API_TOKEN ``` Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information. ## Demo off target The package contains a simple end-to-end demo that downloads pre-trained weights and runs this model on a sample input. ```bash python -m qai_hub_models.models.hrnet_pose_quantized.demo ``` The above demo runs a reference implementation of pre-processing, model inference, and post processing. **NOTE**: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above). ``` %run -m qai_hub_models.models.hrnet_pose_quantized.demo ``` ### Run model on a cloud-hosted device In addition to the demo, you can also run the model on a cloud-hosted Qualcomm® device. This script does the following: * Performance check on-device on a cloud-hosted device * Downloads compiled assets that can be deployed on-device for Android. * Accuracy check between PyTorch and on-device outputs. ```bash python -m qai_hub_models.models.hrnet_pose_quantized.export ``` ``` Profiling Results ------------------------------------------------------------ HRNetPoseQuantized Device : Samsung Galaxy S23 (13) Runtime : TFLITE Estimated inference time (ms) : 1.0 Estimated peak memory usage (MB): [0, 2] Total # Ops : 518 Compute Unit(s) : NPU (518 ops) ``` ## Run demo on a cloud-hosted device You can also run the demo on-device. ```bash python -m qai_hub_models.models.hrnet_pose_quantized.demo --on-device ``` **NOTE**: If you want running in a Jupyter Notebook or Google Colab like environment, please add the following to your cell (instead of the above). ``` %run -m qai_hub_models.models.hrnet_pose_quantized.demo -- --on-device ``` ## Deploying compiled model to Android The models can be deployed using multiple runtimes: - TensorFlow Lite (`.tflite` export): [This tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a guide to deploy the .tflite model in an Android application. - QNN (`.so` export ): This [sample app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html) provides instructions on how to use the `.so` shared library in an Android application. ## View on Qualcomm® AI Hub Get more details on HRNetPoseQuantized's performance across various devices [here](https://aihub.qualcomm.com/models/hrnet_pose_quantized). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## License * The license for the original implementation of HRNetPoseQuantized can be found [here](https://github.com/quic/aimet-model-zoo/blob/develop/LICENSE.pdf). * The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf) ## References * [Deep High-Resolution Representation Learning for Human Pose Estimation](https://arxiv.org/abs/1902.09212) * [Source Model Implementation](https://github.com/quic/aimet-model-zoo/tree/develop/aimet_zoo_torch/hrnet_posenet) ## 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).