scripts: figure generators + frame-regen script for the opencv5 report

make_figures.py gains the DE-landscape, calibration, and per-film leave-one-out
holdout figures used by the experiment log. regen_frame_examples.sh replays all
nine films with the shipped learned-boundary flood config and draws GT-aware
TP/FP/FN frames, so every annotated image in the docs is reproducible.

experiments/regen_frame_examples.sh

@@ -0,0 +1,44 @@
+#!/usr/bin/env bash
+# Regenerate annotated TP/FP/FN frame examples for ALL 9 films against the current
+# opencv5 pipeline (learned-boundary flood, shipped config). Replays each film with
+# --raw-out for bboxes, then dump_error_frames.py draws GT-aware boxes
+# (green TP / red FP / orange unknown / blue FN panel). Frames land in
+# experiments/dump_review/<slug>/ (regenerable; gitignored). Hand-pick the ones a
+# doc needs from there.
+set -uo pipefail
+REPO="/home/dtourolle/Development/scene-actor-extraction"; cd "$REPO"
+export MIOPEN_USER_DB_PATH="$HOME/.cache/miopen-sae"
+GAL=experiments/galleries/gallery_LVFace-B_Glint360K.h5
+LUT=experiments/file-lut.json
+CFG=(--prob-threshold 0.485 --ownership-logodds 1.72 --track-extinction-sec 31
+     --track-alpha 0.435 --evidence-rho-max 0.204 --evidence-admit-below 0.784
+     --match-prior 0.433 --expand-band-lo 0.804 --expand-band-hi 0.952
+     --expand-gallery --presence-mode flood)
+mapfile -t ROWS < <(python3 -c '
+import json
+for f in json.load(open("experiments/manifests/films_LVFace_opencv5.json")):
+    print(f["slug"]+"\t"+f["xray"])')
+SP=/tmp/claude-1000/-home-dtourolle-Development-scene-actor-extraction/c579f8cf-2974-4cbd-be88-afec68dbbf58/scratchpad
+for row in "${ROWS[@]}"; do
+  slug="${row%%$'\t'*}"; xray="${row#*$'\t'}"
+  movie="$(python3 -c "import json;print(json.load(open('$LUT'))['$slug'])")"
+  echo "=== $slug ==="
+  [ -f "experiments/dump_review/$slug/manifest.json" ] && { echo "  exists, skip"; continue; }
+  # replay the learned-boundary (LOO) dump so frames reflect true generalization
+  dump="experiments/dumps/injected_loo/${slug}.h5"
+  [ -f "$dump" ] || dump="experiments/dumps/LVFace-B_Glint360K_opencv5/dump_${slug}.h5"
+  for try in 1 2 3; do
+    timeout 280 python scripts/optimizer/replay.py --dump "$dump" --gallery "$GAL" \
+      --out "$SP/${slug}_pred.json" --raw-out "$SP/${slug}_raw.jsonl" "${CFG[@]}" \
+      >"$SP/${slug}_replay.log" 2>&1 && break
+    echo "  replay try $try failed, retrying"
+  done
+  [ -s "$SP/${slug}_raw.jsonl" ] || { echo "  no raw output, skip"; continue; }
+  python3 scripts/optimizer/dump_error_frames.py \
+    --pred "$SP/${slug}_pred.json" --raw "$SP/${slug}_raw.jsonl" \
+    --xray "$xray" --movie "$movie" --gallery "$GAL" \
+    --out-dir "experiments/dump_review/$slug" --n-per-bucket 4 \
+    >"$SP/${slug}_frames.log" 2>&1
+  echo "  $(grep -oE 'wrote [0-9]+ frames' "$SP/${slug}_frames.log" | tail -1)"
+done
+echo "=== DONE ==="

scripts/scene_detector/make_figures.py

@@ -68,5 +68,51 @@ def fig_evolution():
     ax.set_ylim(0,18)
     fig.tight_layout(); fig.savefig(OUT/"scene_detector_evolution.png"); plt.close(fig)
 
-fig_presence(); fig_macro(); fig_evolution()
+import csv as _csv
-print("wrote:", *(p.name for p in sorted(OUT.glob("scene_*.png"))))
+
+# ── Figure 4: DE convergence (the 10-knob presence sweep) ────────────────────
+def fig_de():
+    import json
+    rows=[json.loads(l) for l in open("experiments/trajectories/lvface_opencv5_10knob.FINAL.jsonl")]
+    f1=[r["f1"]*100 for r in rows]
+    run_best=np.maximum.accumulate(f1)
+    fig,ax=plt.subplots(figsize=(8,4.5))
+    ax.scatter(range(len(f1)),f1,s=8,alpha=0.35,color="#9aa7b4",label="candidate")
+    ax.plot(run_best,color="#3d7ea6",lw=2,label="best so far")
+    ax.set_xlabel("DE evaluation"); ax.set_ylabel("macro presence F1 (%)")
+    ax.set_title("10-knob presence sweep (Differential Evolution)")
+    ax.legend(loc="lower right"); ax.set_ylim(0, max(f1)+8)
+    ax.text(0.02,0.95,f"optimum {max(f1):.1f}%",transform=ax.transAxes,va="top",
+            fontsize=10,bbox=dict(boxstyle="round",fc="#f4f4f4",ec="#ccc"))
+    fig.tight_layout(); fig.savefig(OUT/"de_search_landscape.png"); plt.close(fig)
+
+# ── Figure 5: calibration curve (similarity → P(match)) ──────────────────────
+def fig_calibration():
+    sims,ps=[],[]
+    with open("experiments/galleries/gallery_LVFace-B_Glint360K.h5.calib_cache.csv") as f:
+        for r in _csv.DictReader(f):
+            sims.append(float(r["similarity"])); ps.append(float(r["p_match"]))
+    fig,ax=plt.subplots(figsize=(6.5,4.5))
+    ax.plot(sims,ps,color="#3d7ea6",lw=2)
+    ax.axhline(0.485,ls="--",color="#e07a5f",lw=1,label="shipped threshold 0.485")
+    ax.set_xlabel("cosine similarity"); ax.set_ylabel("calibrated P(match)")
+    ax.set_title("LVFace-B Glint360K calibration"); ax.set_xlim(-1,1); ax.legend()
+    fig.tight_layout(); fig.savefig(OUT/"calibration_curves.png"); plt.close(fig)
+
+# ── Figure 6: holdout F1 by film (learned detector, LOO) ─────────────────────
+def fig_holdout():
+    order=np.argsort(FL)
+    fig,ax=plt.subplots(figsize=(8,4.5))
+    y=np.arange(len(FILMS))
+    ax.barh(y,[FL[i] for i in order],color="#3d7ea6")
+    ax.set_yticks(y); ax.set_yticklabels([FILMS[i] for i in order])
+    ax.set_xlabel("presence F1 (%), learned detector (LOO)")
+    ax.set_title("Per-film presence F1 — leave-one-out")
+    ax.axvline(np.mean(FL),ls="--",color="#333",lw=1)
+    ax.text(np.mean(FL)+1,0.2,f"macro {np.mean(FL):.1f}%",fontsize=9)
+    for i,idx in enumerate(order): ax.text(FL[idx]+0.5,i,f"{FL[idx]:.0f}",va="center",fontsize=8)
+    ax.set_xlim(0,100)
+    fig.tight_layout(); fig.savefig(OUT/"holdout_f1_by_film.png"); plt.close(fig)
+
+fig_presence(); fig_macro(); fig_evolution(); fig_de(); fig_calibration(); fig_holdout()
+print("wrote:", *(p.name for p in sorted(OUT.glob("*.png"))))