Remove stray roxy ONNX export; note the two training-only protocol labels

README.md

@@ -142,7 +142,10 @@ resample back to the original image size.
 ## Output labels
 
 61 channels: `background` at index 0, then 60 anatomical structures in the
-order stored in `label_schema.json` (protocol `all_structures_flexray_v4`):
+order stored in `label_schema.json`. The training protocol
+(`all_structures_flexray_v4`) has 62 foreground labels; its two coarse region
+labels, `lumbar_spine` and `thoracolumbar_spine`, only harmonize datasets that
+label those regions as a block and are not predicted.
 
 - **Skull / shoulder girdle:** skull, scapulae, clavicles
 - **Upper limb:** humeri, radii, ulnae, carpals, metacarpals, phalanges

checksums.json

@@ -1,7 +1,7 @@
 {
   "algorithm": "sha256",
   "files": {
-    "README.md": "e6e5c17b8ece40c296e1fd40d92774a44d6bb6fb1e5452b94f00533ebddf694f",
+    "README.md": "ce0a7a4087fec705e9cfe753bb01a06e0e2b29377e896e31e012f361e97b7058",
     "config.yml": "7c7d52b2404d5e3cb5347036feac994ab8b8a18dd6bef5cfa47b749077af727a",
     "label_schema.json": "c8fa61b6585fc4043e2c51ba1f53271f9313cdae8d812479449b8a2a0ba12d7a",
     "model.safetensors": "716ce3a8fb2a6abe22b2f2188fd596ddc4642b273fb0d336d629448154fc6d24",

onnx/roxy-256-fp16.onnx

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f1c5b7845f3d93ca9d9866f260f62ad82adf273bd8002b4002a768ed900850b8
-size 143632544