MediaPipe-Hand-Detection

qualcomm/MediaPipe-Hand-Detection

MediaPipe-Hand-Detection is a object detection model from qualcomm. Use it when you need objects located in an image. It is set up for pytorch. The card lists the license as apache-2.0.

Downloads · 30 days

1.6K

16% of all-time downloads

All-time downloads

10.4K

Public

Repo size

1.3 GB

Likes

Trending 1

Hugging Face

Repo makeup

Click a slice to open those files.

.md11.9 KB · 77%

At a glance

Task: Object Detection
Library: pytorch
License: apache-2.0
Access: Public
Created: Feb 25, 2024
Updated: Sep 23, 2026
SHA: 8f691f9c

Model card

From the Hugging Face model README

MediaPipe-Hand-Detection: Optimized for Qualcomm Devices

The MediaPipe Hand Landmark Detector is a machine learning pipeline that predicts bounding boxes and pose skeletons of hands in an image.

This is based on the implementation of MediaPipe-Hand-Detection found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up 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 2.50, ONNX Runtime 1.27.1	Download
QNN_DLC	float	Universal	QAIRT 2.50	Download
TFLITE	float	Universal	QAIRT 2.50	Download

For more device-specific assets and performance metrics, visit MediaPipe-Hand-Detection on Qualcomm® AI Hub.

Option 2: Export with Custom Configurations

Use the Qualcomm® AI Hub Models 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 MediaPipe-Hand-Detection on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.object_detection

Model Stats:

Input resolution: 256x256
Model size (hand_detector) (float): 6.75 MB
Model size (hand_landmark_detector) (float): 7.70 MB
Number of parameters (hand_detector): 1.76M
Number of parameters (hand_landmark_detector): 2.01M

Performance Summary

Model	Runtime	Precision	Chipset	Inference Time (ms)	Peak Memory Range (MB)	Primary Compute Unit
hand_detector	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.424 ms	0 - 46 MB	NPU
hand_detector	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.49 ms	0 - 50 MB	NPU
hand_detector	ONNX	float	Snapdragon® X2 Elite	0.475 ms	2 - 2 MB	NPU
hand_detector	ONNX	float	Snapdragon® X Elite	0.861 ms	1 - 1 MB	NPU
hand_detector	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.586 ms	0 - 69 MB	NPU
hand_detector	ONNX	float	Snapdragon® 8 Gen 1 Mobile	1.403 ms	1 - 68 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	1.377 ms	1 - 5 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.832 ms	0 - 6 MB	NPU
hand_detector	ONNX	float	Qualcomm® QCS8450	1.403 ms	1 - 68 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	1.263 ms	1 - 4 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	0.861 ms	1 - 1 MB	NPU
hand_detector	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.49 ms	0 - 50 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.381 ms	1 - 44 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.434 ms	0 - 41 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® X2 Elite	0.619 ms	1 - 1 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® X Elite	0.878 ms	1 - 1 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.531 ms	0 - 61 MB	NPU
hand_detector	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	1.246 ms	1 - 62 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	1.215 ms	1 - 5 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.731 ms	1 - 2 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® SA8650P	1.285 ms	0 - 41 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® SA8255P	1.285 ms	0 - 41 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® QCS8450	1.246 ms	1 - 62 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	1.124 ms	1 - 4 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	0.878 ms	1 - 1 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	0.434 ms	0 - 41 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® SA7255P	3.736 ms	1 - 44 MB	NPU
hand_detector	QNN_DLC	float	Qualcomm® SA8295P	1.51 ms	0 - 34 MB	NPU
hand_detector	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.395 ms	0 - 41 MB	NPU
hand_detector	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.446 ms	0 - 44 MB	NPU
hand_detector	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.523 ms	0 - 60 MB	NPU
hand_detector	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	1.264 ms	0 - 58 MB	NPU
hand_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	1.231 ms	0 - 8 MB	NPU
hand_detector	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.735 ms	0 - 4 MB	NPU
hand_detector	TFLITE	float	Qualcomm® SA8650P	1.302 ms	0 - 41 MB	NPU
hand_detector	TFLITE	float	Qualcomm® SA8255P	1.302 ms	0 - 41 MB	NPU
hand_detector	TFLITE	float	Qualcomm® QCS8450	1.264 ms	0 - 58 MB	NPU
hand_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	1.13 ms	0 - 8 MB	NPU
hand_detector	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	0.446 ms	0 - 44 MB	NPU
hand_detector	TFLITE	float	Qualcomm® SA7255P	3.78 ms	0 - 41 MB	NPU
hand_detector	TFLITE	float	Qualcomm® SA8295P	1.539 ms	0 - 33 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.533 ms	0 - 42 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® 8 Elite For Galaxy Mobile	0.617 ms	0 - 45 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® X2 Elite	0.685 ms	2 - 2 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® X Elite	1.106 ms	6 - 6 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® 8 Gen 3 Mobile	0.801 ms	0 - 64 MB	NPU
hand_landmark_detector	ONNX	float	Snapdragon® 8 Gen 1 Mobile	1.891 ms	1 - 64 MB	NPU
hand_landmark_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-8275	1.983 ms	1 - 5 MB	NPU
hand_landmark_detector	ONNX	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	1.051 ms	0 - 2 MB	NPU
hand_landmark_detector	ONNX	float	Qualcomm® QCS8450	1.891 ms	1 - 64 MB	NPU
hand_landmark_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-9075	1.809 ms	1 - 4 MB	NPU
hand_landmark_detector	ONNX	float	Qualcomm® Dragonwing™ IQ-X7181	1.106 ms	6 - 6 MB	NPU
hand_landmark_detector	ONNX	float	Qualcomm® Dragonwing™ Q-8750	0.617 ms	0 - 45 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.488 ms	1 - 40 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® 8 Elite For Galaxy Mobile	0.572 ms	0 - 37 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® X2 Elite	0.83 ms	1 - 1 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® X Elite	1.206 ms	1 - 1 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® 8 Gen 3 Mobile	0.737 ms	0 - 59 MB	NPU
hand_landmark_detector	QNN_DLC	float	Snapdragon® 8 Gen 1 Mobile	1.774 ms	1 - 60 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-8275	1.807 ms	1 - 4 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.952 ms	1 - 2 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® SA8650P	1.878 ms	0 - 37 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® SA8255P	1.878 ms	0 - 37 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® QCS8450	1.774 ms	1 - 60 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-9075	1.624 ms	3 - 6 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® Dragonwing™ IQ-X7181	1.206 ms	1 - 1 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® Dragonwing™ Q-8750	0.572 ms	0 - 37 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® SA7255P	5.29 ms	1 - 39 MB	NPU
hand_landmark_detector	QNN_DLC	float	Qualcomm® SA8295P	2.067 ms	0 - 33 MB	NPU
hand_landmark_detector	TFLITE	float	Snapdragon® 8 Elite Gen 5 For Galaxy Mobile	0.497 ms	0 - 42 MB	NPU
hand_landmark_detector	TFLITE	float	Snapdragon® 8 Elite For Galaxy Mobile	0.577 ms	0 - 46 MB	NPU
hand_landmark_detector	TFLITE	float	Snapdragon® 8 Gen 3 Mobile	0.731 ms	0 - 62 MB	NPU
hand_landmark_detector	TFLITE	float	Snapdragon® 8 Gen 1 Mobile	1.769 ms	0 - 66 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-8275	1.817 ms	0 - 10 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® Dragonwing™ QCS8550 (Proxy)	0.945 ms	0 - 2 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® SA8650P	1.871 ms	0 - 43 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® SA8255P	1.871 ms	0 - 43 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® QCS8450	1.769 ms	0 - 66 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® Dragonwing™ IQ-9075	1.621 ms	0 - 10 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® Dragonwing™ Q-8750	0.577 ms	0 - 46 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® SA7255P	5.311 ms	0 - 43 MB	NPU
hand_landmark_detector	TFLITE	float	Qualcomm® SA8295P	2.082 ms	0 - 37 MB	NPU

License

The license for the original implementation of MediaPipe-Hand-Detection can be found here.

References

Community

Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
For questions or feedback please reach out to us.

Task: Object Detection
Library: pytorch
License: apache-2.0
Created: Feb 25, 2024
Updated: Sep 23, 2026