Pass the avatar config explicitly; degas_eval no longer back-fills it

README.md

@@ -68,12 +68,18 @@ python degas_eval.py \
     --dat_dir "$PWD/DREAMS-AVATAR/data/P1C2" \
     --ip none \
     --model_path "$PWD/weights/avatars/P1_smplx" \
-    --configs configs/degas_config.yaml,configs/degas_vae_driver.yaml,configs/dreams/p1_train_base.yaml,configs/dreams/p1_face_B.yaml \
+    --configs "$PWD/weights/avatars/P1_smplx/config.yaml" \
     dataset.cache_dir="$PWD/cache/P1C2_eval_cam3" \
     dataset.test.cam_select=[3] \
     "dataset.test.frm_list=np.arange(0, 293, 8).tolist()"
 ```
 
+**You pass the avatar's config yourself.** `degas_eval.py` does not read the run's
+`config.yaml` behind your back; it used to append it last, which let a training-time value
+silently outrank the command line. Each avatar here ships a portable, fully resolved
+`config.yaml` (`dat_dir: ???`, no machine-specific paths), so naming it alone is enough.
+Anything required but missing is reported by name up front, not deep inside the model.
+
 **`--model_path` must be absolute.** A relative one is resolved *inside* `--dat_dir`
 (`os.path.join(dat_dir, model_path)`), because that is where a training run writes by
 default, so `weights/avatars/P1_smplx` fails with a `FileNotFoundError` on a path you never
@@ -81,9 +87,9 @@ typed. Hence `$PWD`.
 
 Three more things fail quietly rather than loudly, so they are worth stating plainly:
 
-1. **The run's saved `config.yaml` is applied last**, so an avatar is always evaluated
-   under its own face setting. Only CLI overrides outrank it, which is why the test split
-   is set on the command line above.
+1. **Pass the avatar's own `config.yaml`**, or it is not evaluated under the settings it was
+   trained with. Command-line `key=value` overrides still outrank every config file, which
+   is why the test split is set that way above.
 2. **Give every capture its own `dataset.cache_dir`.** Decoded frames are named
    `cam%02d/%08d.jpg` with no capture in the path, so a shared cache would serve P1C1's
    frame 110 for P1C2's frame 110.
@@ -93,7 +99,8 @@ Three more things fail quietly rather than loudly, so they are worth stating pla
    `--dat_dir` on their own. A config saved by your own training run holds an absolute path
    to the training session's codes instead, and there you must override it.
 
-For `P1_dpe`, swap the face config to `configs/dreams/p1_face_A_dpe.yaml`.
+For `P1_dpe`, point `--model_path` and `--configs` at that avatar instead, and add
+`dataset.with_face_dpe=` for the session you are driving with.
 
 ## Training setup