Keep the dense landmarks behind each eye reading, packed

The 106 points the eye boxes were cut from, stored beside the reading as
16-bit fixed point over the frame: 424 bytes a face, a seventh of a pixel
on a 6000-pixel frame, where f16 at the same size would have been six.
Derived data like the embedding, kept for the same reason — it cost a
fetch and a model run, and the next per-face pass should run from the
catalog. Shards carry it; a peer's shard from before it is still read.
This commit is contained in:
2026-09-19 14:24:15 +02:00
parent 85cc2b1dcc
commit facb44cb55
10 changed files with 264 additions and 99 deletions
+46 -46
View File
File diff suppressed because one or more lines are too long