Hfelabs/ergocapture-models

RTMW3D-X, float16-weight ONNX (for ErgoCapture)

Smaller download of RTMW3D-X (rtmw3d-x_8xb64_cocktail14-384x288), a 133-keypoint whole-body 3D pose model from OpenMMLab MMPose (Apache-2.0), based on the ONNX export at Soykaf/RTMW3D-x.

Used by ErgoCapture, an in-browser ergonomic posture assessment app.

What changed

• Weights are stored as float16 and cast back to float32 inside the graph; ONNX Runtime folds the casts when the session loads, so computation stays float32. Download size: 369 MB → 187 MB.
• The SimCC output head (last layers, ~3.7 MB) is kept in float32.
• Inputs and outputs are unchanged (input 1×3×384×288 float32; SimCC x / y / z outputs).

Check against the original

On real image crops, 95.5–100% of SimCC argmax positions are identical and the rest differ by one bin (0.5 px), except three of 1,197 keypoint axes where the original model itself had two near-equal peaks (a thumb tip with score 0.42, one toe depth and one face point).

sha256: dc276b94339c17d459902baad32652606ade51df1f8b3effb96b130b4a9e5f7a

License

Apache-2.0, as the original RTMW3D model. Copyright of the original weights: OpenMMLab contributors.