dtourolle
6f0ad83a55
Optimizer (scripts/optimizer/): replay.py runs the real C++ tracker/matcher/ scene_tracker chain over a dumped-embeddings HDF5 via sae_kpn, so a threshold sweep never re-decodes video or re-embeds faces. optimize.py drives scipy's differential_evolution over the knob space, with DE-level parallelism (multiple population candidates evaluated concurrently via a ThreadPoolExecutor) on top of per-film replay parallelism. second_score.py is the per-second X-Ray scoring metric (TPI/FPI/FN, out-of-cast misID weighted 10x, fair recall masked to gallery-known cast) that superseded an earlier scene-union metric. dump_error_frames.py / dump_scene_montage.py extract annotated video frames (bounding boxes, TPI/FPI/FN captions, onscreen-vs-offscreen split) for visual review of a replay against ground truth. Gallery utilities: cast_restrict.py, gallery_membership.py, fetch_missing_actors.py, reembed_gallery.py. scripts/validation/: X-Ray ground-truth loading and provider-agnostic identity matching (identity.py's keys_for — an actor is the union of every id we can derive, since pipeline output and ground truth don't share one id space). scripts/artifacts/: push/pull scripts for the Gitea generic package registry — galleries, montage frames, and experiment data (manifests/trajectories/results) are pushed there instead of committed, since none are needed to run the app, only benchmarks. Versioned by git short-SHA. scripts/docs/: MkDocs site build (build_site.sh) and the calibration-curve comparison chart (calibration_chart.py, matplotlib, reads each gallery's embedded calibration). Gallery-building scripts (make_jellyfin_gallery.py, make_gallery.py, filter_gallery.py, run_from_jellyfin.py, movienet_eval.py, movienet_prep.py, sae_gallery.py) updated to read/write HDF5 galleries exclusively, matching the engine-side format switch. run_from_jellyfin.py and the optimizer no longer carry movie source paths in shared manifests (some source filenames include scene-release tags) — resolved locally via a gitignored file-lut.json instead.
72 lines
2.5 KiB
Bash
Executable File
72 lines
2.5 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
# Pre-build TensorRT engines for ArcFace and SCRFD with the same shape profiles
|
||
# the runtime nodes use. First-run ORT engine builds take 30–90 s per model and
|
||
# block the pipeline; this script does it offline so cold starts are instant.
|
||
#
|
||
# Profiles must match src/arcface_embedder.hpp and src/scrfd_decoder.hpp:
|
||
# ArcFace : min=1x3x112x112 opt=Nx3x112x112 max=Nx3x112x112 (N = embed batch)
|
||
# SCRFD : 1x3x640x640 (fixed; we letterbox to this)
|
||
# TransNetV2 : 1x100x27x48x3 (fixed; scene detector window), input tensor "input"
|
||
#
|
||
# These trtexec-built engines are *not* picked up by the ORT TRT EP cache —
|
||
# ORT uses its own engine format. The point of this script is:
|
||
# (a) sanity-check that the ONNX models build under TRT at all;
|
||
# (b) measure pure inference latency without ORT overhead.
|
||
# Run scene_analyze normally and ORT will populate ./trt_cache itself.
|
||
set -euo pipefail
|
||
|
||
ROOT="$(cd "$(dirname "$0")/.." && pwd)"
|
||
MODELS="$ROOT/models"
|
||
OUT="$ROOT/trt_cache"
|
||
mkdir -p "$OUT"
|
||
|
||
EMBED_BATCH="${EMBED_BATCH:-4}"
|
||
ARCFACE_MODEL="${ARCFACE_MODEL:-$MODELS/arcface_w600k_r50.onnx}"
|
||
SCRFD_MODEL="${SCRFD_MODEL:-$MODELS/scrfd_500m_bnkps.onnx}"
|
||
SCENE_MODEL="${SCENE_MODEL:-$MODELS/transnetv2.onnx}"
|
||
|
||
run() { echo "+ $*"; "$@"; }
|
||
|
||
echo "== ArcFace =="
|
||
run trtexec \
|
||
--onnx="$ARCFACE_MODEL" \
|
||
--fp16 \
|
||
--minShapes=input.1:1x3x112x112 \
|
||
--optShapes=input.1:${EMBED_BATCH}x3x112x112 \
|
||
--maxShapes=input.1:${EMBED_BATCH}x3x112x112 \
|
||
--saveEngine="$OUT/arcface.$(basename "$ARCFACE_MODEL" .onnx).b${EMBED_BATCH}.fp16.engine" \
|
||
--useCudaGraph
|
||
|
||
echo
|
||
echo "== SCRFD =="
|
||
run trtexec \
|
||
--onnx="$SCRFD_MODEL" \
|
||
--fp16 \
|
||
--minShapes=input.1:1x3x640x640 \
|
||
--optShapes=input.1:1x3x640x640 \
|
||
--maxShapes=input.1:1x3x640x640 \
|
||
--saveEngine="$OUT/scrfd.$(basename "$SCRFD_MODEL" .onnx).640.fp16.engine" \
|
||
--useCudaGraph
|
||
|
||
if [[ -f "$SCENE_MODEL" ]]; then
|
||
echo
|
||
echo "== TransNetV2 (scene detector) =="
|
||
# Fixed 1x100x27x48x3 window. The raw-TRT scene detector backend loads this
|
||
# engine directly via --scene-detector-engine; the ORT-TRT EP builds its own.
|
||
run trtexec \
|
||
--onnx="$SCENE_MODEL" \
|
||
--fp16 \
|
||
--minShapes=input:1x100x27x48x3 \
|
||
--optShapes=input:1x100x27x48x3 \
|
||
--maxShapes=input:1x100x27x48x3 \
|
||
--saveEngine="$OUT/transnetv2.100x27x48.fp16.engine" \
|
||
--useCudaGraph
|
||
else
|
||
echo
|
||
echo "== TransNetV2 skipped (no $SCENE_MODEL) =="
|
||
fi
|
||
|
||
echo
|
||
echo "Engines saved under: $OUT"
|
||
echo "Look for 'mean: ... ms' in each section for per-call latency."
|