fix(bundle): carry the Hailo HEF in the offline bundle, ONNX optional (P5-3)
The air-gapped bundle never fetched the Hailo HEF, so an offline Hailo install had no pose model. Two latent breaks also made the offline path unusable regardless of P5-3: - build [2/5] ran `fetch_movenet` unconditionally; with the MoveNet source unreachable that aborted the whole build under `set -e`. - install_offline copied only `*.onnx`, so even a HEF placed in the bundle never reached $PREFIX/models for the backend gate to find. Fixes: - build_offline_bundle.sh fetches the $HAILO_ARCH (default hailo8) HEF via edge.tools.fetch_hailo_hef (pinned sha256, aborts on mismatch) and stages yolov8s_pose.hef. MoveNet ONNX is now optional (guarded fetch → Hailo-only bundle if unavailable). onnxruntime moves to a best-effort optional wheel. MANIFEST lists models + available pose_backends. - install_offline.sh copies *.hef (and tolerates a missing *.onnx). Tests (test_deploy_artifacts.py): bundle fetches+stages the HEF, MoveNet is optional (guarded), installer copies the HEF. Both scripts pass `bash -n`. Full python suite: 152 passed, 2 skipped. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_019Xmn8KZWqiQUguEMRtn6rW
This commit is contained in:
유창욱
parent
99070f5e87
commit
1fb7a5da58
4 changed files with 85 additions and 10 deletions
|
|
@ -25,7 +25,12 @@ WHEELHOUSE="$STAGE/wheelhouse"
|
|||
PYVER="${PYVER:-3.11}" # Pi OS Bookworm ships CPython 3.11
|
||||
PYABI="cp${PYVER//./}" # cp311
|
||||
TARGET_ARCH="${TARGET_ARCH:-aarch64}"
|
||||
RUNTIME_PKGS=(numpy requests onnxruntime opencv-python-headless)
|
||||
HAILO_ARCH="${HAILO_ARCH:-hailo8}" # 26 TOPS AI HAT+ (Hailo-8); set hailo8l for the 13 TOPS AI Kit
|
||||
# Mandatory for EVERY backend (cv2/numpy/requests are on the unconditional startup chain).
|
||||
# onnxruntime is the CPU-MoveNet fallback only and publishes no 32-bit-ARM wheel / no sdist, so
|
||||
# it is downloaded best-effort — a Hailo bundle need not carry it (install_offline treats it optional).
|
||||
RUNTIME_PKGS=(numpy requests opencv-python-headless)
|
||||
OPTIONAL_PKGS=(onnxruntime)
|
||||
|
||||
MODE="native"
|
||||
[ "${1:-}" = "--cross" ] && MODE="cross"
|
||||
|
|
@ -33,12 +38,13 @@ MODE="native"
|
|||
echo ">> build mode : $MODE"
|
||||
echo ">> python target : $PYVER ($PYABI)"
|
||||
echo ">> target arch : $TARGET_ARCH"
|
||||
echo ">> hailo arch : $HAILO_ARCH"
|
||||
echo ">> output : $OUT_DIR"
|
||||
|
||||
rm -rf "$STAGE"
|
||||
mkdir -p "$WHEELHOUSE" "$STAGE/src" "$STAGE/models" "$STAGE/deploy/systemd" "$STAGE/docs"
|
||||
|
||||
echo ">> [1/5] downloading runtime wheels -> wheelhouse/"
|
||||
echo ">> [1/6] downloading runtime wheels -> wheelhouse/"
|
||||
if [ "$MODE" = "cross" ]; then
|
||||
# Best-effort cross download. Try the common manylinux aarch64 tags.
|
||||
python3 -m pip download \
|
||||
|
|
@ -47,6 +53,14 @@ if [ "$MODE" = "cross" ]; then
|
|||
--platform "manylinux2014_${TARGET_ARCH}" \
|
||||
--platform "manylinux_2_28_${TARGET_ARCH}" \
|
||||
-d "$WHEELHOUSE" "${RUNTIME_PKGS[@]}"
|
||||
# CPU fallback wheel, best-effort — onnxruntime may have no matching aarch64/$PYABI tag.
|
||||
python3 -m pip download \
|
||||
--only-binary=:all: \
|
||||
--python-version "$PYVER" --implementation cp --abi "$PYABI" \
|
||||
--platform "manylinux2014_${TARGET_ARCH}" \
|
||||
--platform "manylinux_2_28_${TARGET_ARCH}" \
|
||||
-d "$WHEELHOUSE" "${OPTIONAL_PKGS[@]}" \
|
||||
|| echo " -> onnxruntime aarch64/$PYABI wheel unavailable; Hailo-only bundle (no CPU MoveNet)."
|
||||
else
|
||||
# Native: wheels for THIS host's interpreter/arch (run on the Pi / arm64 CI).
|
||||
# Guard the ABI: numpy/onnxruntime ship version-specific cpXY wheels, so a build
|
||||
|
|
@ -69,35 +83,56 @@ else
|
|||
exit 1
|
||||
fi
|
||||
python3 -m pip download -d "$WHEELHOUSE" "${RUNTIME_PKGS[@]}"
|
||||
# CPU fallback wheel, best-effort — a Hailo bundle is complete without it.
|
||||
python3 -m pip download -d "$WHEELHOUSE" "${OPTIONAL_PKGS[@]}" \
|
||||
|| echo " -> onnxruntime unavailable for this host; Hailo-only bundle (no CPU MoveNet)."
|
||||
fi
|
||||
|
||||
echo ">> [2/5] fetching MoveNet ONNX model (build-machine only)"
|
||||
( cd "$REPO_ROOT" && python3 -m edge.tools.fetch_movenet )
|
||||
echo ">> [2/6] fetching MoveNet ONNX model (optional CPU fallback; build-machine only)"
|
||||
# Optional: the MoveNet source may be unreachable, and a Hailo-8 delivery runs off the HEF. Do
|
||||
# not abort the whole bundle over the CPU fallback — stage it if we can, otherwise carry on.
|
||||
if ( cd "$REPO_ROOT" && python3 -m edge.tools.fetch_movenet ); then
|
||||
cp "$REPO_ROOT/models/movenet_lightning.onnx" "$STAGE/models/"
|
||||
else
|
||||
echo " -> MoveNet ONNX unavailable; Hailo-only bundle (CPU fallback not included)."
|
||||
fi
|
||||
|
||||
echo ">> [3/5] staging edge source (package + pyproject)"
|
||||
echo ">> [3/6] fetching Hailo $HAILO_ARCH yolov8s_pose HEF (build-machine only)"
|
||||
# Mandatory for a Hailo delivery: this is the primary pose backend. fetch_hailo_hef verifies the
|
||||
# download against a pinned sha256 and refuses a mismatch, so a bad/tampered HEF aborts the build.
|
||||
( cd "$REPO_ROOT" && HAILO_ARCH="$HAILO_ARCH" python3 -m edge.tools.fetch_hailo_hef --arch "$HAILO_ARCH" )
|
||||
cp "$REPO_ROOT/models/yolov8s_pose.hef" "$STAGE/models/"
|
||||
|
||||
echo ">> [4/6] staging edge source (package + pyproject)"
|
||||
cp -r "$REPO_ROOT/edge" "$STAGE/src/edge"
|
||||
cp "$REPO_ROOT/pyproject.toml" "$STAGE/src/"
|
||||
# do not ship compiled caches
|
||||
find "$STAGE/src" -name '__pycache__' -type d -prune -exec rm -rf {} +
|
||||
|
||||
echo ">> [4/5] staging deploy assets + install script"
|
||||
echo ">> [5/6] staging deploy assets + install script"
|
||||
cp "$REPO_ROOT/deploy/systemd/move-detect-edge.service" "$STAGE/deploy/systemd/"
|
||||
cp "$REPO_ROOT/deploy/systemd/move-detect-edge.env.example" "$STAGE/deploy/systemd/"
|
||||
cp "$REPO_ROOT/deploy/bundle/install_offline.sh" "$STAGE/"
|
||||
cp "$REPO_ROOT/docs/pilot-runbook.md" "$STAGE/docs/" 2>/dev/null || true
|
||||
chmod +x "$STAGE/install_offline.sh"
|
||||
|
||||
# Which pose backends this bundle can actually run, so the operator knows before it crosses the
|
||||
# air gap. Hailo needs the HEF (present) + system hailo_platform on the Pi; MoveNet needs the ONNX.
|
||||
HAS_ONNX=no; [ -f "$STAGE/models/movenet_lightning.onnx" ] && HAS_ONNX=yes
|
||||
{
|
||||
echo "bundle: move-detect-edge"
|
||||
echo "built_mode: $MODE"
|
||||
echo "python: $PYVER ($PYABI)"
|
||||
echo "target_arch: $TARGET_ARCH"
|
||||
echo "hailo_arch: $HAILO_ARCH"
|
||||
echo "pose_backends: hailo (yolov8s_pose.hef)$([ "$HAS_ONNX" = yes ] && echo ', movenet (movenet_lightning.onnx)')"
|
||||
echo "models:"
|
||||
ls -1 "$STAGE/models"
|
||||
echo "wheels:"
|
||||
ls -1 "$WHEELHOUSE"
|
||||
} > "$STAGE/MANIFEST.txt"
|
||||
|
||||
echo ">> [5/5] packaging tarball"
|
||||
echo ">> [6/6] packaging tarball"
|
||||
TARBALL="$OUT_DIR/move-detect-edge-bundle-${TARGET_ARCH}-${PYABI}.tar.gz"
|
||||
tar -C "$OUT_DIR" -czf "$TARBALL" "move-detect-edge-bundle"
|
||||
echo ">> DONE: $TARBALL"
|
||||
|
|
|
|||
|
|
@ -39,7 +39,11 @@ install -d -m 0755 "$PREFIX" "$PREFIX/src" "$PREFIX/models" "$PREFIX/docs"
|
|||
rm -rf "$PREFIX/src/edge"
|
||||
cp -r "$HERE/src/edge" "$PREFIX/src/edge"
|
||||
cp "$HERE/src/pyproject.toml" "$PREFIX/src/" 2>/dev/null || true
|
||||
cp "$HERE/models/"*.onnx "$PREFIX/models/"
|
||||
# Copy whichever pose models the bundle carries. Each is optional on its own — a Hailo bundle
|
||||
# ships only the .hef, a CPU bundle only the .onnx — so a missing glob must not abort the install
|
||||
# (the [5/6] backend gate below is what refuses a bundle with NO usable backend).
|
||||
cp "$HERE/models/"*.hef "$PREFIX/models/" 2>/dev/null || true
|
||||
cp "$HERE/models/"*.onnx "$PREFIX/models/" 2>/dev/null || true
|
||||
cp "$HERE/docs/"*.md "$PREFIX/docs/" 2>/dev/null || true
|
||||
|
||||
echo ">> [3/6] python venv + offline wheel install (--no-index)"
|
||||
|
|
|
|||
|
|
@ -206,9 +206,16 @@ misconfig/degradation fail LOUD.
|
|||
- [x] **P5-2 [H]** `deploy/bundle/build_offline_bundle.sh:55` — a native build on x86 produces
|
||||
an aarch64-named tarball full of x86_64 wheels. **Fix:** assert `uname -m == TARGET_ARCH`.
|
||||
DONE — native branch now hard-fails when uname -m != TARGET_ARCH.
|
||||
- [ ] **P5-3 [M]** `deploy/bundle/build_offline_bundle.sh:65` — the air-gapped bundle never
|
||||
- [x] **P5-3 [M]** `deploy/bundle/build_offline_bundle.sh:65` — the air-gapped bundle never
|
||||
carries the Hailo HEF, so offline Hailo install is impossible. **Fix:** stage the HEF (via
|
||||
`fetch_hailo_hef --arch`) into the bundle.
|
||||
DONE — build now fetches the `$HAILO_ARCH` (default hailo8) HEF via `fetch_hailo_hef` (pinned
|
||||
sha256, aborts on mismatch) and stages `yolov8s_pose.hef`. Also fixed two latent breaks that
|
||||
made the offline path unusable regardless: the MoveNet ONNX fetch was unconditional so its dead
|
||||
source aborted the whole build under `set -e` (now guarded/optional → Hailo-only bundle), and
|
||||
`install_offline.sh` copied only `*.onnx` so a bundled HEF never reached `$PREFIX/models` for the
|
||||
backend gate to find (now copies `*.hef` too). MANIFEST lists models + available pose_backends.
|
||||
Tests: fetches/stages HEF, MoveNet optional, installer copies the HEF.
|
||||
- [ ] **P5-4 [M]** `deploy/bundle/build_offline_bundle.sh:28` — pip deps unpinned, no digests,
|
||||
MANIFEST has no hashes, bundle unsigned; spec requires SHA256/GPG + SBOM. **Fix:** pin +
|
||||
hash + manifest digests.
|
||||
|
|
|
|||
|
|
@ -10,6 +10,8 @@ UNIT = os.path.join(DEPLOY, "move-detect-edge.service")
|
|||
SETUP_ONLINE = os.path.join(os.path.dirname(__file__), "..", "deploy", "setup_online.sh")
|
||||
INSTALL_OFFLINE = os.path.join(os.path.dirname(__file__), "..", "deploy", "bundle",
|
||||
"install_offline.sh")
|
||||
BUILD_OFFLINE = os.path.join(os.path.dirname(__file__), "..", "deploy", "bundle",
|
||||
"build_offline_bundle.sh")
|
||||
|
||||
# Keys the daemon consumes (edge/config.py:load_config + edge/daemon.py:main).
|
||||
REQUIRED_ENV = {
|
||||
|
|
@ -214,3 +216,30 @@ def test_offline_installer_gates_the_pose_backend():
|
|||
assert "no usable pose backend" in sh
|
||||
# It must WRITE the reconciled backend into the installed env, not leave the template's.
|
||||
assert "POSE_BACKEND=$POSE_BACKEND" in sh or "POSE_BACKEND=${POSE_BACKEND}" in sh
|
||||
|
||||
|
||||
def test_offline_bundle_fetches_and_stages_the_hailo_hef():
|
||||
with open(BUILD_OFFLINE, encoding="utf-8") as f:
|
||||
sh = f.read()
|
||||
# A Hailo-8 delivery runs off the HEF; the offline bundle must carry it, fetched on the build
|
||||
# machine (the air-gapped Pi cannot). Without this the installer's backend gate finds no HEF.
|
||||
assert "edge.tools.fetch_hailo_hef" in sh
|
||||
assert "yolov8s_pose.hef" in sh # staged into the bundle's models/
|
||||
|
||||
|
||||
def test_offline_bundle_treats_movenet_onnx_as_optional():
|
||||
with open(BUILD_OFFLINE, encoding="utf-8") as f:
|
||||
sh = f.read()
|
||||
# The MoveNet source can be unreachable and a Hailo bundle is complete without the CPU
|
||||
# fallback, so the fetch must be GUARDED (inside an `if`) — never an unconditional line that
|
||||
# aborts the whole build under `set -e`.
|
||||
assert "fetch_movenet ); then" in sh
|
||||
assert "Hailo-only bundle" in sh
|
||||
|
||||
|
||||
def test_offline_installer_copies_the_hef_into_place():
|
||||
with open(INSTALL_OFFLINE, encoding="utf-8") as f:
|
||||
sh = f.read()
|
||||
# install_offline used to copy only *.onnx, so a HEF in the bundle never reached
|
||||
# $PREFIX/models and the Hailo backend gate ([5/6]) could never see it.
|
||||
assert 'cp "$HERE/models/"*.hef' in sh
|
||||
|
|
|
|||
Loading…
Reference in a new issue