RTMPose-Face WFLW LiteRT fp16 (fully-GPU, Pixel 8a corr 0.9995, 4ms)

README.md

@@ -0,0 +1,45 @@
+---
+license: apache-2.0
+library_name: LiteRT
+pipeline_tag: keypoint-detection
+tags: [litert, tflite, on-device, android, gpu, face-alignment, face-landmarks, rtmpose, wflw, mmpose]
+base_model: open-mmlab/mmpose
+---
+
+# RTMPose-Face (WFLW) — LiteRT (on-device 98-point face alignment, fully-GPU)
+
+[RTMPose](https://github.com/open-mmlab/mmpose) (mmpose) face alignment, trained on **WFLW**, converted to
+**LiteRT** and running **fully on the `CompiledModel` GPU** (ML Drift) on Android. **98 dense facial landmarks**
+(contour, eyebrows, eyes, nose, mouth, pupils) — the dense complement to a 5-point face detector.
+
+![RTMPose-Face — 98-point WFLW face mesh on-device LiteRT GPU](samples/sample.png)
+
+## On-device (Pixel 8a, Tensor G3 — verified)
+
+| | |
+|---|---|
+| nodes on GPU | **333 / 333** LITERT_CL (full residency) |
+| inference | **~4 ms** (256×256) |
+| size | 33.6 MB (fp16) |
+| accuracy | device-vs-PyTorch SimCC corr **0.9995**, 98 landmarks |
+
+```
+face[1,3,256,256] (mmpose mean/std) →[GPU: RTMPose-m]→ simcc_x[1,98,512], simcc_y[1,98,512]
+```
+
+output[0] = simcc_x, output[1] = simcc_y; each landmark = `argmax` over its 1D SimCC (bins = pixels × 2).
+
+## How it converts (litert-torch) — the RTMPose recipe, unchanged
+
+Same model family as the human-pose RTMPose; only the config/checkpoint change to WFLW. The two on-device-only
+Mali fixes transfer **without modification**: **`ScaleNorm` → SafeRMSNorm** and **GAU `act@act` BMM →
+broadcast-reduce**. banned ops NONE, ≤4D, tflite-vs-torch corr **1.0**, device-vs-torch **0.9995**.
+
+## Preprocessing
+
+Center-crop to a (centered) face, resize 256×256, mmpose mean/std (RGB, 0-255 scale), NCHW.
+
+## License
+
+[Apache-2.0](https://github.com/open-mmlab/mmpose/blob/main/LICENSE). Upstream:
+[open-mmlab/mmpose](https://github.com/open-mmlab/mmpose); dataset [WFLW](https://wywu.github.io/projects/LAB/WFLW.html).

rtm_face_fp16.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:652788790a2dac0ff117e5bc33c17eeb7048fd7ac0e6642e98b9fb60e65e24c7
+size 33622896