dtourolle/DarkRoom
1
0
Fork 0
Code Issues 39 Pull Requests Actions Packages Projects Releases 20 Wiki Activity

S15.4, CPU half: XFeat runs in ~400 ms per frame on the tablet

Browse Source 
tools/onnx-probe-on-device.sh cross-builds dr-segment's onnx_probe
without the embedded segmentation model, pushes it with a model to the
attached device and times two runs. The 768×1024 XFeat export takes
~400 ms on the reference tablet's NEON cores against ~300 ms on the
desktop, with identical output ranges — inside NFR-MRG-1's 1 s per frame.
The blend half of S15.4 waits for a chunked blend to exist.
This commit is contained in:
dtourolle
2026-09-19 15:24:12 +02:00
parent 5bf06c5030
commit 2bf0ec8dba
3 changed files with 71 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/requirements.md
+3 -2
View File
@@ -1839,8 +1839,9 @@ touched by a resize. That is the list in the criterion, and it is the testable h
**NFR-MRG-1 — Merge latency.** For five 24 MP frames: the alignment preview (FR-MRG-7) within
5 s on the reference desktop and 15 s on the reference tablet, of which keypoint detection is at
most 1 s per frame on the tablet's CPU; the full merge written to disk within 60 s on the desktop.
The tablet's full-merge figure is set by S15, not guessed here.
most 1 s per frame on the tablet's CPU (measured 2026-09-19 at ~0.4 s, S15.4); the full merge
written to disk within 60 s on the desktop. The tablet's full-merge figure is set by S15's blend
measurement, not guessed here.
**Performance regressions fail the build.** §8's benchmark suite runs per-commit; a regression
beyond a stated tolerance is a build failure, not a notification. Performance work rots otherwise.