--- library_name: pytorch license: apache-2.0 pipeline_tag: object-detection tags: - real_time - android --- ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/mediapipe_hand/web-assets/model_demo.png) # MediaPipe-Hand-Detection: Optimized for Mobile Deployment ## Real-time hand detection optimized for mobile and edge The MediaPipe Hand Landmark Detector is a machine learning pipeline that predicts bounding boxes and pose skeletons of hands in an image. This model is an implementation of MediaPipe-Hand-Detection found [here](https://github.com/zmurez/MediaPipePyTorch/). This repository provides scripts to run MediaPipe-Hand-Detection on Qualcomm® devices. More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/mediapipe_hand). ### Model Details - **Model Type:** Object detection - **Model Stats:** - Input resolution: 256x256 - Number of parameters (MediaPipeHandDetector): 1.76M - Model size (MediaPipeHandDetector): 6.76 MB - Number of parameters (MediaPipeHandLandmarkDetector): 2.01M - Model size (MediaPipeHandLandmarkDetector): 7.71 MB | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model |---|---|---|---|---|---|---|---|---| | MediaPipeHandDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 0.709 ms | 0 - 8 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) | | MediaPipeHandDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.182 ms | 0 - 54 MB | FP16 | NPU | [MediaPipe-Hand-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.onnx) | | MediaPipeHandDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.521 ms | 0 - 59 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) | | MediaPipeHandDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 0.853 ms | 0 - 67 MB | FP16 | NPU | [MediaPipe-Hand-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.onnx) | | MediaPipeHandDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.521 ms | 0 - 28 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) | | MediaPipeHandDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 0.876 ms | 0 - 32 MB | FP16 | NPU | [MediaPipe-Hand-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.onnx) | | MediaPipeHandDetector | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 0.703 ms | 0 - 4 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) | | MediaPipeHandDetector | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 0.705 ms | 0 - 4 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) | | MediaPipeHandDetector | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 0.704 ms | 0 - 3 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) | | MediaPipeHandDetector | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 0.712 ms | 0 - 3 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) | | MediaPipeHandDetector | SA8295P ADP | SA8295P | TFLITE | 1.75 ms | 0 - 22 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) | | MediaPipeHandDetector | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 1.29 ms | 0 - 52 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.tflite) | | MediaPipeHandDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.21 ms | 4 - 4 MB | FP16 | NPU | [MediaPipe-Hand-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandDetector.onnx) | | MediaPipeHandLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 1.01 ms | 0 - 1 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) | | MediaPipeHandLandmarkDetector | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 1.537 ms | 0 - 8 MB | FP16 | NPU | [MediaPipe-Hand-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.onnx) | | MediaPipeHandLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 0.75 ms | 0 - 62 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) | | MediaPipeHandLandmarkDetector | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 1.15 ms | 0 - 65 MB | FP16 | NPU | [MediaPipe-Hand-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.onnx) | | MediaPipeHandLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 0.692 ms | 0 - 31 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) | | MediaPipeHandLandmarkDetector | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 1.067 ms | 0 - 37 MB | FP16 | NPU | [MediaPipe-Hand-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.onnx) | | MediaPipeHandLandmarkDetector | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 1.005 ms | 0 - 1 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) | | MediaPipeHandLandmarkDetector | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 1.007 ms | 0 - 3 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) | | MediaPipeHandLandmarkDetector | SA8775 (Proxy) | SA8775P Proxy | TFLITE | 1.032 ms | 0 - 2 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) | | MediaPipeHandLandmarkDetector | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 1.061 ms | 0 - 2 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) | | MediaPipeHandLandmarkDetector | SA8295P ADP | SA8295P | TFLITE | 4.528 ms | 0 - 35 MB | FP16 | GPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) | | MediaPipeHandLandmarkDetector | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 2.635 ms | 0 - 55 MB | FP16 | NPU | [MediaPipe-Hand-Detection.tflite](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.tflite) | | MediaPipeHandLandmarkDetector | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 1.65 ms | 8 - 8 MB | FP16 | NPU | [MediaPipe-Hand-Detection.onnx](https://huggingface.co/qualcomm/MediaPipe-Hand-Detection/blob/main/MediaPipeHandLandmarkDetector.onnx) | ## Installation This model can be installed as a Python package via pip. ```bash pip install qai-hub-models ``` ## 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.mediapipe_hand.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.mediapipe_hand.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.mediapipe_hand.export ``` ``` Profiling Results ------------------------------------------------------------ MediaPipeHandDetector Device : Samsung Galaxy S23 (13) Runtime : TFLITE Estimated inference time (ms) : 0.7 Estimated peak memory usage (MB): [0, 8] Total # Ops : 149 Compute Unit(s) : NPU (149 ops) ------------------------------------------------------------ MediaPipeHandLandmarkDetector Device : Samsung Galaxy S23 (13) Runtime : TFLITE Estimated inference time (ms) : 1.0 Estimated peak memory usage (MB): [0, 1] Total # Ops : 158 Compute Unit(s) : NPU (158 ops) ``` ## How does this work? This [export script](https://aihub.qualcomm.com/models/mediapipe_hand/qai_hub_models/models/MediaPipe-Hand-Detection/export.py) leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model on-device. Lets go through each step below in detail: Step 1: **Compile model for on-device deployment** To compile a PyTorch model for on-device deployment, we first trace the model in memory using the `jit.trace` and then call the `submit_compile_job` API. ```python import torch import qai_hub as hub from qai_hub_models.models.mediapipe_hand import MediaPipeHandDetector,MediaPipeHandLandmarkDetector # Load the model hand_detector_model = MediaPipeHandDetector.from_pretrained() hand_landmark_detector_model = MediaPipeHandLandmarkDetector.from_pretrained() # Device device = hub.Device("Samsung Galaxy S23") # Trace model hand_detector_input_shape = hand_detector_model.get_input_spec() hand_detector_sample_inputs = hand_detector_model.sample_inputs() traced_hand_detector_model = torch.jit.trace(hand_detector_model, [torch.tensor(data[0]) for _, data in hand_detector_sample_inputs.items()]) # Compile model on a specific device hand_detector_compile_job = hub.submit_compile_job( model=traced_hand_detector_model , device=device, input_specs=hand_detector_model.get_input_spec(), ) # Get target model to run on-device hand_detector_target_model = hand_detector_compile_job.get_target_model() # Trace model hand_landmark_detector_input_shape = hand_landmark_detector_model.get_input_spec() hand_landmark_detector_sample_inputs = hand_landmark_detector_model.sample_inputs() traced_hand_landmark_detector_model = torch.jit.trace(hand_landmark_detector_model, [torch.tensor(data[0]) for _, data in hand_landmark_detector_sample_inputs.items()]) # Compile model on a specific device hand_landmark_detector_compile_job = hub.submit_compile_job( model=traced_hand_landmark_detector_model , device=device, input_specs=hand_landmark_detector_model.get_input_spec(), ) # Get target model to run on-device hand_landmark_detector_target_model = hand_landmark_detector_compile_job.get_target_model() ``` Step 2: **Performance profiling on cloud-hosted device** After compiling models from step 1. Models can be profiled model on-device using the `target_model`. Note that this scripts runs the model on a device automatically provisioned in the cloud. Once the job is submitted, you can navigate to a provided job URL to view a variety of on-device performance metrics. ```python hand_detector_profile_job = hub.submit_profile_job( model=hand_detector_target_model, device=device, ) hand_landmark_detector_profile_job = hub.submit_profile_job( model=hand_landmark_detector_target_model, device=device, ) ``` Step 3: **Verify on-device accuracy** To verify the accuracy of the model on-device, you can run on-device inference on sample input data on the same cloud hosted device. ```python hand_detector_input_data = hand_detector_model.sample_inputs() hand_detector_inference_job = hub.submit_inference_job( model=hand_detector_target_model, device=device, inputs=hand_detector_input_data, ) hand_detector_inference_job.download_output_data() hand_landmark_detector_input_data = hand_landmark_detector_model.sample_inputs() hand_landmark_detector_inference_job = hub.submit_inference_job( model=hand_landmark_detector_target_model, device=device, inputs=hand_landmark_detector_input_data, ) hand_landmark_detector_inference_job.download_output_data() ``` With the output of the model, you can compute like PSNR, relative errors or spot check the output with expected output. **Note**: This on-device profiling and inference requires access to Qualcomm® AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup). ## 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 MediaPipe-Hand-Detection's performance across various devices [here](https://aihub.qualcomm.com/models/mediapipe_hand). Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/) ## License * The license for the original implementation of MediaPipe-Hand-Detection can be found [here](https://github.com/zmurez/MediaPipePyTorch/blob/master/LICENSE). * 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 * [MediaPipe Hands: On-device Real-time Hand Tracking](https://arxiv.org/abs/2006.10214) * [Source Model Implementation](https://github.com/zmurez/MediaPipePyTorch/) ## 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).