Add model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags: [robotics, surface-roughness, grinding, contrastive-learning]
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# grind — visual_grind_grading checkpoints
|
| 7 |
+
|
| 8 |
+
Trained artifacts for the `visual_grind_grading` approach of the
|
| 9 |
+
[grind](https://github.com/BabaYaga840/grind) repo. Gitignored there; hydrate
|
| 10 |
+
a fresh clone with `./pull_checkpoints.sh`.
|
| 11 |
+
|
| 12 |
+
Contents:
|
| 13 |
+
- `outputs/roi_cnn/roi_cnn.pt` — TinyNet ROI CNN weights (state_dict).
|
| 14 |
+
- `cache/*.npz` — p27–p38 embedding caches (multisession / SupCon / RNC
|
| 15 |
+
experiments + sandpaper validation embeddings) for reproducing analyses
|
| 16 |
+
without recompute.
|