Update card: RNC grader

README.md

@@ -1,16 +1,31 @@
 ---
 license: mit
-tags: [robotics, surface-roughness, grinding, contrastive-learning]
+tags: [robotics, surface-roughness, grinding, contrastive-learning, RNC]
 ---
 
 # grind — visual_grind_grading checkpoints
 
 Trained artifacts for the `visual_grind_grading` approach of the
-[grind](https://github.com/BabaYaga840/grind) repo. Gitignored there; hydrate
-a fresh clone with `./pull_checkpoints.sh`.
+[grind](https://github.com/BabaYaga840/grind) repo. Gitignored there; hydrate a
+fresh clone with `./pull_checkpoints.sh`.
 
-Contents:
-- `outputs/roi_cnn/roi_cnn.pt` — TinyNet ROI CNN weights (state_dict).
+## Grading model (RNC)
+`outputs/rnc_grader/rnc_sandpaper_grader.pt` — the RNC sandpaper Ra grader.
+`torch.load` gives a dict: `Enc` encoder `state_dict` (3-conv CNN, dim 32) +
+per-grit `anchors` + `grit_classes` + `Ra_by_grit`. Inference:
+
+```python
+import torch, torch.nn.functional as F, numpy as np
+c = torch.load("rnc_sandpaper_grader.pt", weights_only=False)
+# rebuild Enc (see scripts/shared_grading.py: class Enc), load c["state_dict"]
+def illum_norm(x): m=x.mean((2,3),keepdim=True); s=x.std((2,3),keepdim=True)+1e-4; return (x-m)/s
+z = F.normalize(net(illum_norm(x)), dim=1).cpu().numpy()          # x: (N,3,64,64) [0,1]
+w = np.exp(z @ c["anchors"].T / c["tau"]); w /= w.sum(1, keepdims=True)
+grade = w @ c["grit_classes"].astype("float32")                  # soft ordinal, 0..6
+```
+Validated leave-angle-out rho ~0.93 vs true grit (real, texture-grounded).
+
+## Other artifacts
+- `outputs/roi_cnn/roi_cnn.pt` — TinyNet ROI CNN weights (grinding ROI, state_dict).
 - `cache/*.npz` — p27–p38 embedding caches (multisession / SupCon / RNC
-  experiments + sandpaper validation embeddings) for reproducing analyses
-  without recompute.
+  experiments) for reproducing analyses without recompute.