2D Coordinates of predicted keypoints are provided for each skeleton detected.
All predictions / model inferences are made completely on-device.
No internet connection is required to interpret images or video.
No internet dependency means super-fast performance.
Fast: Optimized for speed, best for processing video streams in real-time or on older devices.
Accurate: Optimized for higher accuracy where prediction quality is more important than speed.
Small: Optimized for size, keep your application bundle size low and conserve bandwidth.
Supported mobile platforms:
Runs on live video with a fast frame rate.
Exact FPS performance varies depending on device, but it is possible to run this feature on live video on modern mobile devices.
Uses a MobileNet backbone
2D Coordinates of each keypoint detected
Number of keypoints detected
The confidence associated with each detection
Core ML, TensorFlow, TensorFlow Mobile, TensorFlow Lite, Keras
25 FPS on iPhone X
7 FPS on Pixel 2