Add causal person fusion and MuVAP stage-3 baselines

infer_turn_head.py

@@ -19,6 +19,7 @@ from easycom_head import (
     NUM_HORIZONS,
     OFFICIAL_TEST_SESSIONS,
     STEP_SECONDS,
+    TRACK_PERSON_FUSION_MODES,
     TurnPredictionHead,
     average_precision_metrics,
     checkpoint_head_config,
@@ -149,7 +150,7 @@ def _predict_states(
                 start,
                 min(start + batch_size, len(states)),
             )
-            if head.local_fusion == "track-gru-residual":
+            if head.local_fusion in TRACK_PERSON_FUSION_MODES:
                 person_batch, person_mask = local_person_features.padded_history(
                     rows,
                     max_observations=head.person_history_frames,
@@ -500,6 +501,14 @@ def main() -> None:
             f"{name}: saved pred {predictions.shape}, "
             f"causal-valid counts={valid.sum(axis=0).tolist()}"
         )
+        if head.person_adapter_diagnostics():
+            print(
+                "person adapter diagnostics: "
+                + json.dumps(
+                    head.person_adapter_diagnostics(),
+                    sort_keys=True,
+                )
+            )
 
     metrics = _evaluate(session_predictions, session_valid, session_targets)
     transition_metrics = (
@@ -532,10 +541,23 @@ def main() -> None:
             ).get("epochs"),
             "checkpoint_train_sessions": checkpoint_payload.get("train_sessions"),
             "checkpoint_dev_sessions": checkpoint_payload.get("dev_sessions"),
+            "initialized_pooled_checkpoint": checkpoint_payload.get(
+                "training_config", {}
+            ).get("initialize_pooled_checkpoint"),
+            "initialized_pooled_checkpoint_sha256": checkpoint_payload.get(
+                "training_config", {}
+            ).get("initialize_pooled_checkpoint_sha256"),
+            "initialized_pooled_checkpoint_epoch": checkpoint_payload.get(
+                "training_config", {}
+            ).get("initialize_pooled_checkpoint_epoch"),
+            "pooled_base_frozen": checkpoint_payload.get(
+                "training_config", {}
+            ).get("pooled_base_frozen"),
             "layer_fusion": head.layer_fusion,
             "local_fusion": head.local_fusion,
             "local_fusion_scope": LOCAL_FUSION_SCOPES[head.local_fusion],
             "person_interaction_gates": head.person_interaction_gates(),
+            "person_adapter_diagnostics": head.person_adapter_diagnostics(),
             "person_history_frames": head.person_history_frames,
             "person_track_max_gap_seconds": head.person_track_max_gap_seconds,
             "local_contract": local_contract,