RTMPose-Hand — LiteRT (on-device 21-keypoint hand pose, fully-GPU)
RTMPose (mmpose, CSPNeXt + RTMCC/SimCC head)
hand pose, converted to LiteRT and running fully on the CompiledModel GPU (ML Drift) on Android.
The 21 standard hand keypoints (wrist + 4 joints × 5 fingers) for a single centered hand.
On-device (Pixel 8a, Tensor G3 — verified)
| nodes on GPU | 333 / 333 LITERT_CL (full residency) |
| inference | ~4 ms (256×256) |
| size | 28 MB (fp16) |
| accuracy | device-vs-PyTorch SimCC corr 0.999, 21/21 keypoints |
image[1,3,256,256] (ImageNet 0-255) →[GPU: CSPNeXt + RTMCC]→ simcc_x[1,21,512], simcc_y[1,21,512]
How it converts (litert-torch)
Identical RTMPose-family recipe (both numerically exact, no PixelShuffle since there's no neck):
ScaleNorm(RMS) → SafeRMSNorm — fp16-overflow all-zero-head fix (scale x down by S=64 before squaring).- GAU
act@actBMM → broadcast-multiply + reduce-sum.
Result: banned ops NONE, all tensors ≤4D, tflite-vs-torch corr 1.0, device-vs-torch corr 0.999.
Preprocessing
Center-crop to square, resize to 256×256, ImageNet 0-255 normalize, NCHW. Top-down — one centered hand. SimCC argmax (÷ split=2) → pixel.
License
Apache-2.0. Upstream: open-mmlab/mmpose RTMPose-Hand.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support