feat: add causal frame set attention fusion

This commit is contained in:
Xin Wang
2026-09-02 18:48:26 +08:00
parent e769094b3d
commit 8e70281330
8 changed files with 837 additions and 38 deletions
+7
View File
@@ -43,6 +43,13 @@ result.
- Ego4D batch and 8-GPU local-feature launchers, with strict frame audits.
- Timing-derived wearer floor-state and event diagnostics.
### Implemented, awaiting remote runtime verification
- F1 Frame-set Attention loader/head/train/infer path. It uses fused G+A as
one query over the latest half-open causal person set, retains direct A in
the head, and dynamically pads people per batch. Do not report it as a
measured method until the L20 smoke and full controls pass.
### Current blocker
`evaluate_floor_state_changes.py` counts a wearer transition anywhere in a