feat(engine): PersonDetector.detect_batch — batched inference primitive (P4 foundation)#97
Merged
Merged
Conversation
…tive (P4) Letterboxes N frames, one session.run → [N,3,S,S], parses each output slice with the same logic as detect() so detect_batch(frames)[i] == detect(frames[i]). Degrades gracefully to a per-frame detect() loop for fixed-batch-1 ONNX exports. 9 new tests; 1015 total passed. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Merged
TCVinNYC
added a commit
that referenced
this pull request
Jun 24, 2026
Second **pre-release** of the 2.2.0 reliability + performance roadmap, for real-hardware validation before the stable 2.2.0. Bumps `__version__` to `2.2.0-rc2`; on merge, tag `v2.2.0-rc2` triggers the pre-release installer build. **New since rc1 (all merged, CI-green + multi-agent-reviewed):** - #92 CPU subservice governor — fewer CPU spikes (phase-stagger) + cadence throttle under load - #93 preview-rate-cap (~20fps) - #90 live GPU-acceleration verdict in the Services panel - #91 OpenVINO auto-install for Intel - #94 scene-adaptive ReID threshold - #95/#96 opt-in fused TargetAssociator (off by default) - #97 batched detect_batch primitive **Validate especially:** CPU usage/spikes with all subservices running (your priority), and \`python -m autoptz --bench\` / the Services-panel verdict on Intel-Mac+AMD. To try the new tracking logic, set \`tracking.use_target_associator = true\`. Follow-ups after your validation: P4 coalescing scheduler, wire the associator ReID/pose cues + flip its default, int8 CPU quant, stable Win/Linux device binding. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Foundation for cross-camera batching (P4): adds
PersonDetector.detect_batch(frames)— letterbox N frames into one[N,3,S,S]tensor, ONEsession.run, parse each output slice exactly as the single-framedetect()does. Returns onelist[Detection]per frame;detect_batch(frames)[i]is guaranteed equal todetect(frames[i])(batching is a pure perf optimization).detect()(counter saved/restored) so the method is always correct regardless of export. The true N>1 batched path runs on dynamic-batch detectors.detect()(single-frame) is untouched;detect_intervalgating is left to callers (documented).Scope: the primitive only. The cross-thread COALESCING scheduler (collect concurrent per-camera detect() calls within a small window → one batched run; behind a flag) is the follow-up — it is GPU-throughput-focused (not CPU) and needs a real multi-cam GPU rig to validate. Noted, not built here.
🤖 Generated with Claude Code