feat(tooling): X-Ray threshold optimizer, gallery utilities, artifact registry, docs build
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X-Ray scoring metric (TPI/FPI/FN, out-of-cast misID weighted 10x, fair recall masked to gallery-known cast) that superseded an earlier scene-union metric.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.
This commit is contained in:
@@ -0,0 +1,135 @@
|
||||
#!/usr/bin/env python3
|
||||
"""
|
||||
tmdb_imdb_map.py — build & consult a cached tmdb_person_id → imdb_id crosswalk.
|
||||
|
||||
The gallery (and pipeline output) key actors by TMDB person id but carry no IMDb
|
||||
`nm…` id, while the X-Ray / MovieNet ground truth keys on IMDb. Rather than join on
|
||||
fuzzy names, we resolve tmdb→imdb once via TMDB's authoritative
|
||||
`/person/{id}/external_ids` endpoint and cache the result to JSON. The eval loaders
|
||||
consult this table to add an exact `imdb:` key alongside each `tmdb:` key.
|
||||
|
||||
Table format (JSON): { "<tmdb_person_id>": "nm0000123" | null, ... }
|
||||
A null means "looked up, TMDB has no IMDb id" — cached so we don't re-query.
|
||||
|
||||
Build / refresh the table:
|
||||
python scripts/validation/tmdb_imdb_map.py \
|
||||
--gallery gallery_arcface_w600k_r50.json \
|
||||
--out scripts/validation/tmdb_imdb.json
|
||||
# TMDB_API_KEY read from env / .env (via sae_env)
|
||||
|
||||
Consult it from code:
|
||||
from tmdb_imdb_map import CrosswalkTable
|
||||
tbl = CrosswalkTable.load("scripts/validation/tmdb_imdb.json")
|
||||
nm = tbl.imdb_for("35467") # -> "nm..." or None
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import sys
|
||||
import time
|
||||
from pathlib import Path
|
||||
|
||||
_HERE = Path(__file__).resolve().parent
|
||||
|
||||
|
||||
class CrosswalkTable:
|
||||
"""Read-only view over the cached tmdb→imdb JSON. Missing file → empty table."""
|
||||
|
||||
def __init__(self, mapping: dict[str, str | None]):
|
||||
self._m = mapping
|
||||
|
||||
@classmethod
|
||||
def load(cls, path: str | Path) -> "CrosswalkTable":
|
||||
p = Path(path)
|
||||
if not p.exists():
|
||||
return cls({})
|
||||
return cls(json.loads(p.read_text()))
|
||||
|
||||
def imdb_for(self, tmdb_id) -> str | None:
|
||||
if tmdb_id is None:
|
||||
return None
|
||||
return self._m.get(str(tmdb_id))
|
||||
|
||||
def __len__(self) -> int:
|
||||
return sum(1 for v in self._m.values() if v)
|
||||
|
||||
|
||||
# ── builder ─────────────────────────────────────────────────────────────────
|
||||
|
||||
def _external_ids(tmdb_get, tmdb_person_id: str, token: str) -> str | None:
|
||||
data = tmdb_get(f"/person/{tmdb_person_id}/external_ids", token)
|
||||
imdb = data.get("imdb_id")
|
||||
return imdb or None # normalize "" → None
|
||||
|
||||
|
||||
def build(gallery_path: str, out_path: str, token: str, sleep: float = 0.0) -> None:
|
||||
# import the existing TMDB helper (scripts/ is the parent dir)
|
||||
sys.path.insert(0, str(_HERE.parent))
|
||||
from sae_tmdb import tmdb_get
|
||||
|
||||
with open(gallery_path) as f:
|
||||
actors = json.load(f).get("actors", [])
|
||||
tmdb_ids = sorted({str(a["tmdb_id"]) for a in actors if a.get("tmdb_id")})
|
||||
print(f"[map] gallery tmdb ids: {len(tmdb_ids)}", file=sys.stderr)
|
||||
|
||||
out = Path(out_path)
|
||||
existing: dict[str, str | None] = {}
|
||||
if out.exists():
|
||||
existing = json.loads(out.read_text())
|
||||
print(f"[map] resuming from {len(existing)} cached entries", file=sys.stderr)
|
||||
|
||||
todo = [t for t in tmdb_ids if t not in existing]
|
||||
print(f"[map] to resolve: {len(todo)}", file=sys.stderr)
|
||||
|
||||
n_ok = n_none = n_err = 0
|
||||
for i, tid in enumerate(todo, 1):
|
||||
try:
|
||||
nm = _external_ids(tmdb_get, tid, token)
|
||||
existing[tid] = nm
|
||||
n_ok += (nm is not None)
|
||||
n_none += (nm is None)
|
||||
except Exception as e: # network/rate-limit/404 — record nothing, keep going
|
||||
n_err += 1
|
||||
print(f"\n[map] error on tmdb {tid}: {e}", file=sys.stderr)
|
||||
if i % 25 == 0 or i == len(todo):
|
||||
print(f"\r[map] {i}/{len(todo)} resolved "
|
||||
f"(imdb={n_ok} none={n_none} err={n_err})", end="", file=sys.stderr)
|
||||
out.write_text(json.dumps(existing, indent=2)) # checkpoint
|
||||
if sleep:
|
||||
time.sleep(sleep)
|
||||
|
||||
out.write_text(json.dumps(existing, indent=2))
|
||||
print(f"\n[map] wrote {out} — {sum(1 for v in existing.values() if v)} imdb ids",
|
||||
file=sys.stderr)
|
||||
|
||||
|
||||
def main():
|
||||
# load .env → os.environ (same convention as the gallery builders)
|
||||
sys.path.insert(0, str(_HERE.parent))
|
||||
try:
|
||||
import sae_env # noqa: F401 (side-effect import)
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
p = argparse.ArgumentParser(description=__doc__,
|
||||
formatter_class=argparse.RawDescriptionHelpFormatter)
|
||||
p.add_argument("--gallery", required=True, help="gallery.json (source of tmdb ids)")
|
||||
p.add_argument("--out", default=str(_HERE / "tmdb_imdb.json"),
|
||||
help="output crosswalk JSON (default: scripts/validation/tmdb_imdb.json)")
|
||||
p.add_argument("--tmdb-key", default=os.environ.get("TMDB_API_KEY"),
|
||||
help="TMDB v3 API key or v4 read token. Env: TMDB_API_KEY")
|
||||
p.add_argument("--sleep", type=float, default=0.0,
|
||||
help="seconds between requests (TMDB has no hard limit; use if throttled)")
|
||||
args = p.parse_args()
|
||||
|
||||
if not args.tmdb_key:
|
||||
sys.exit("[map] no TMDB key — set TMDB_API_KEY or pass --tmdb-key")
|
||||
|
||||
build(args.gallery, args.out, args.tmdb_key, args.sleep)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Reference in New Issue
Block a user