Files
scene-actor-extraction/scripts/artifacts/pull_artifacts.sh
dtourolle 4925443e56 docs: four focused findings pages (best model, gallery scope, expansion, deep dive)
Splits the rep4 write-up's key findings into their own linkable pages:
- best-model.md: calibration curves first (discriminative power, independent
  of any threshold), then F1 on the benchmark — LVFace-B Glint360K wins both.
- gallery-scope.md: whole vs. cast-restricted gallery, isolated from model and
  expansion choice — restriction wins on every axis, but isn't a shipped
  runtime feature yet.
- pose-expansion.md: the training-set expand_gallery effect, and the held-out
  replication attempt that found it doesn't reproduce (5 films, 2 models,
  after catching and fixing a replay-timeout truncation bug and a bbox
  first-match-instead-of-best-match bug in the comparison harness itself). An
  honest null result, with the methodology errors documented since they're
  exactly the kind that manufacture a false "it works!" finding.
- lvface-deep-dive.md: the winning model's held-out generalization gap, its
  two failure modes (frozen-bbox ghost tracks), and a verified case (cross-
  checked against Jellyfin's independent cast metadata) where LVFace
  correctly identified an actor that X-Ray's ground truth failed to credit.

Adds a "report-highlights" artifact-registry package (scripts/artifacts/
push_artifacts.sh, pull_artifacts.sh) for hand-picked illustrative frames that
aren't reproducible via the automated best/worst montage selection, and wires
pulling it into scripts/docs/build_site.sh.
2026-07-19 19:40:19 +02:00

123 lines
4.6 KiB
Bash
Executable File

#!/bin/bash
# pull_artifacts.sh — download benchmark artifacts (galleries, montage frames) from
# the Gitea generic package registry. Counterpart to push_artifacts.sh.
#
# Downloads are public (no token needed) as long as the repo/packages are public.
# Resolving "latest" needs GITEA_TOKEN (the list-packages endpoint requires auth
# on this instance even for a public account) — export it before using "latest".
#
# Usage:
# scripts/artifacts/pull_artifacts.sh galleries [version]
# scripts/artifacts/pull_artifacts.sh montage-frames <film-slug> [version]
# scripts/artifacts/pull_artifacts.sh experiment-data [version]
# scripts/artifacts/pull_artifacts.sh report-highlights <name> [version]
# version defaults to "latest" (newest uploaded version, by created_at).
set -euo pipefail
REPO_ROOT="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
OWNER="dtourolle"
# NOTE: file download lives under /api/packages/ (no /v1/); listing/metadata
# lives under the regular /api/v1/packages/ REST API. Different base paths,
# both real — see push_artifacts.sh's comment.
DL_BASE="https://gitea.tourolle.paris/api/packages/${OWNER}"
resolve_latest_version() {
local package="$1"
if [ -z "${GITEA_TOKEN:-}" ]; then
echo "error: resolving 'latest' needs GITEA_TOKEN (list-packages requires auth here)." >&2
echo " export GITEA_TOKEN=... or pass an explicit version instead of 'latest'." >&2
exit 1
fi
curl -sf "https://gitea.tourolle.paris/api/v1/packages/${OWNER}" \
-H "Authorization: token ${GITEA_TOKEN}" \
| python3 -c "
import json, sys
d = json.load(sys.stdin)
matches = [p for p in d if p['name'] == '$package' and p['type'] == 'generic']
if not matches:
sys.exit('no versions found for package \'$package\'')
matches.sort(key=lambda p: p['created_at'])
print(matches[-1]['version'])
"
}
pull_galleries() {
local version="$1"
local dest="${REPO_ROOT}/experiments/galleries"
mkdir -p "$dest"
echo "=== galleries (version ${version}) ==="
for model in arcface_w600k_r50 arcface_r18 arcface_w600k_mbf LVFace-B_Glint360K; do
local f="gallery_${model}.h5"
echo " fetching ${f}..."
curl -sf "${DL_BASE}/generic/galleries/${version}/${f}" \
-o "${dest}/${f}" || echo " [warn] ${f} not found at version ${version}"
done
}
pull_montage_frames() {
local version="$1" film="$2"
local dest="${REPO_ROOT}/experiments/results/holdout/montage_bestworst"
mkdir -p "$dest"
echo "=== montage-frames/${film} (version ${version}) ==="
local tmp; tmp="$(mktemp)"
curl -sf "${DL_BASE}/generic/montage-frames/${version}/${film}.zip" -o "$tmp"
mkdir -p "${dest}/${film}"
unzip -qo "$tmp" -d "${dest}/${film}"
rm "$tmp"
}
pull_experiment_data() {
local version="$1"
echo "=== experiment-data (version ${version}) ==="
local tmp; tmp="$(mktemp)"
curl -sf "${DL_BASE}/generic/experiment-data/${version}/experiment-data.zip" -o "$tmp"
unzip -qo "$tmp" -d "$REPO_ROOT"
rm "$tmp"
}
pull_report_highlight() {
local version="$1" name="$2"
local dest="${REPO_ROOT}/docs/assets/images"
mkdir -p "$dest"
echo "=== report-highlights/${name} (version ${version}) ==="
curl -sf "${DL_BASE}/generic/report-highlights/${version}/${name}" -o "${dest}/${name}"
}
if [ $# -eq 0 ]; then
echo "usage: $0 galleries [version]" >&2
echo " $0 montage-frames <film-slug> [version]" >&2
echo " $0 experiment-data [version]" >&2
echo " $0 report-highlights <name> [version]" >&2
exit 1
fi
TARGET="$1"
case "$TARGET" in
galleries)
VERSION="${2:-latest}"
[ "$VERSION" = "latest" ] && VERSION="$(resolve_latest_version galleries)"
pull_galleries "$VERSION"
;;
montage-frames)
FILM="${2:?usage: $0 montage-frames <film-slug> [version]}"
VERSION="${3:-latest}"
[ "$VERSION" = "latest" ] && VERSION="$(resolve_latest_version montage-frames)"
pull_montage_frames "$VERSION" "$FILM"
;;
experiment-data)
VERSION="${2:-latest}"
[ "$VERSION" = "latest" ] && VERSION="$(resolve_latest_version experiment-data)"
pull_experiment_data "$VERSION"
;;
report-highlights)
NAME="${2:?usage: $0 report-highlights <name> [version]}"
VERSION="${3:-latest}"
[ "$VERSION" = "latest" ] && VERSION="$(resolve_latest_version report-highlights)"
pull_report_highlight "$VERSION" "$NAME"
;;
*)
echo "unknown target: $TARGET (expected galleries, montage-frames, experiment-data, or report-highlights)" >&2
exit 1
;;
esac