Amc Setup Calibration Stack

docker ps

REPO_URL="https://github.com/NVIDIA-AI-IOT/auto-magic-calib.git"
DEFAULT_CLONE_DIR="$HOME/auto-magic-calib"
CURRENT_GIT_ROOT="$(git rev-parse --show-toplevel 2>/dev/null || true)"

is_amc_checkout() {
  [ -n "$1" ] \
    && [ -f "$1/README.md" ] \
    && grep -q "AutoMagicCalib" "$1/README.md" 2>/dev/null \
    && [ -f "$1/compose/compose.yml" ] \
    && grep -q "auto-magic-calib-ms" "$1/compose/ms/compose.yml" 2>/dev/null \
    && grep -q "auto-magic-calib-ui" "$1/compose/ui/compose.yml" 2>/dev/null
}

REPO_ROOT=""
for candidate in \
  "$CURRENT_GIT_ROOT" \
  "${CURRENT_GIT_ROOT:+$CURRENT_GIT_ROOT/tools/auto-magic-calib}" \
  "${DEEPSTREAM_REPO_ROOT:+$DEEPSTREAM_REPO_ROOT/tools/auto-magic-calib}" \
  "$PWD/tools/auto-magic-calib" \
  "$DEFAULT_CLONE_DIR"; do
  if is_amc_checkout "$candidate"; then
    REPO_ROOT="$candidate"
    echo "✓ Using auto-magic-calib checkout: $REPO_ROOT"
    break
  fi
done

if [ -z "$REPO_ROOT" ]; then
  if [ -n "$CURRENT_GIT_ROOT" ] && [ -d "$CURRENT_GIT_ROOT/tools/auto-magic-calib" ]; then
    echo "Found $CURRENT_GIT_ROOT/tools/auto-magic-calib, but it is not an initialized AMC checkout."
    echo "If running from the DeepStream repository root:"
    echo "  git submodule update --init tools/auto-magic-calib"
  fi

  # Nothing usable on disk — STOP and ask the user for confirmation using the
  # host's question mechanism; if none is available, ask in chat and wait.
  # Do NOT clone silently from this block or clone over a tracked submodule path.
  echo "No usable auto-magic-calib checkout found. Ask the user for confirmation:"
  echo "  Clone $REPO_URL into $DEFAULT_CLONE_DIR? [y/N]"
  echo "On 'y' — run: git clone \"$REPO_URL\" \"$DEFAULT_CLONE_DIR\""
  exit 1
fi

cd "$REPO_ROOT"
export REPO_ROOT
echo "REPO_ROOT=$REPO_ROOT"

# Create a venv for HuggingFace CLI (project-local preferred)
REPO_DIR="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
HF_VENV="${REPO_DIR}/venv"
python3 -m venv "$HF_VENV" 2>/dev/null || {
  echo "ERROR: python3-venv not available." >&2
  echo "Install it manually: sudo apt install -y python3-venv python3-pip" >&2
  exit 1
}

# Install HuggingFace hub (needed for VGGT download)
"$HF_VENV/bin/pip" install --upgrade pip huggingface_hub

echo "<NGC_API_KEY>" | docker login nvcr.io --username '$oauthtoken' --password-stdin
echo "✓ NGC authentication complete"

export REPO_ROOT=$(git rev-parse --show-toplevel)
cd "$REPO_ROOT"

if [ -f "models/vggt/vggt_1B_commercial.pt" ]; then
  echo "✓ VGGT model already present"
else
  echo "✗ VGGT model not found"
  echo "Options:"
  echo "  1. Continue without VGGT (AMC only - sufficient for most use cases)"
  echo "  2. Download VGGT model (~4.7GB, requires HuggingFace account)"
fi

REPO_DIR="$(git rev-parse --show-toplevel 2>/dev/null || pwd)"
cd "$REPO_DIR"

# Find the HuggingFace CLI binary (named 'hf', not 'huggingface-cli')
HF_BIN="$(find "$REPO_DIR/venv" ~/venv/amc -name hf -type f 2>/dev/null | head -1)"
{ [ -z "$HF_BIN" ] || [ ! -x "$HF_BIN" ]; } && { echo "ERROR: hf binary not found or not executable; install the hf CLI (Step 0c) or set HF_BIN" >&2; exit 1; }

# Do NOT use --token on the command line (leaks via ps/argv). The HF CLI
# reads HF_TOKEN from the environment automatically.
HF_TOKEN="<HF_TOKEN>" "$HF_BIN" download facebook/VGGT-1B-Commercial \
  --local-dir models/vggt/

# Verify
ls -lh models/vggt/vggt_1B_commercial.pt
# Should show ~4.7GB file

cd $REPO_ROOT/compose

# Find available backend port (8000-8009)
for port in {8000..8009}; do
  if ! lsof -Pi :$port -sTCP:LISTEN -t >/dev/null 2>&1; then
    MS_PORT=$port
    echo "Using backend port: $MS_PORT"
    break
  fi
done
[ -z "$MS_PORT" ] && { echo "ERROR: no free backend port in 8000-8009; free one or widen the range." >&2; exit 1; }

# Find available UI port (5000-5009)
for port in {5000..5009}; do
  if ! lsof -Pi :$port -sTCP:LISTEN -t >/dev/null 2>&1; then
    UI_PORT=$port
    echo "Using UI port: $UI_PORT"
    break
  fi
done
[ -z "$UI_PORT" ] && { echo "ERROR: no free UI port in 5000-5009; free one or widen the range." >&2; exit 1; }

# Get host IP
HOST_IP=$(hostname -I | awk '{print $1}')
echo "Host IP: $HOST_IP"

# Preserve existing keys and restrict permissions on the Compose environment file.
COMPOSE_ENV_BASENAME="env"
ENV_FILE=".${COMPOSE_ENV_BASENAME}"
if [ -f "$ENV_FILE" ]; then
  BACKUP="${ENV_FILE}.bak.$(date +%s)"
  cp "$ENV_FILE" "$BACKUP"
  chmod 600 "$BACKUP"
fi
touch "$ENV_FILE"
chmod 600 "$ENV_FILE"
set_env_key() {
  local k="$1" v="$2"
  if grep -qE "^${k}=" "$ENV_FILE"; then
    sed -i "s|^${k}=.*|${k}=${v}|" "$ENV_FILE"
  else
    echo "${k}=${v}" >> "$ENV_FILE"
  fi
}
set_env_key AUTO_MAGIC_CALIB_MS_PORT "${MS_PORT}"
set_env_key AUTO_MAGIC_CALIB_UI_PORT "${UI_PORT}"
set_env_key PROJECT_DIR "../../projects"
set_env_key MODEL_DIR "../../models"
set_env_key HOST_IP "${HOST_IP}"

# Keep timestamped Compose environment backups out of git.
GITIGNORE="$REPO_ROOT/.gitignore"
touch "$GITIGNORE"
BACKUP_PATTERN="compose/${ENV_FILE}.bak.*"
grep -qxF "$BACKUP_PATTERN" "$GITIGNORE" || echo "$BACKUP_PATTERN" >> "$GITIGNORE"

echo "✓ Compose environment file updated"
cat "$ENV_FILE"

cd "$REPO_ROOT"

# Create projects directory if it doesn't exist
mkdir -p projects

# Set ownership (required for containers to write calibration outputs).
# Do this AFTER VGGT download is complete (current user needs write access during download).
# Get explicit user confirmation before running sudo chown — it recursively changes
# ownership of $REPO_ROOT/projects and $REPO_ROOT/models to UID/GID 1000.
[ -d projects ] && [ -d models ] || {
  echo "ERROR: expected projects/ and models/ under $REPO_ROOT" >&2; exit 1;
}
echo "About to chown -R 1000:1000 on:"
echo "  $REPO_ROOT/projects"
echo "  $REPO_ROOT/models"
echo "(required because containers run as UID 1000). Confirm before proceeding."
sudo chown 1000:1000 -R projects
sudo chown 1000:1000 -R models

echo "✓ Permissions set"

cd $REPO_ROOT/compose

# Fail-fast image-access check: confirm the NGC key can reach every release
# image BEFORE pulling. `docker manifest inspect` checks registry access without
# downloading layers, and the image list is read from the resolved compose so it
# tracks the release tag automatically.
IMAGES=$(docker compose config --images | sort -u)
[ -z "$IMAGES" ] && { echo "ERROR: no images resolved from compose — check the Compose environment settings and chosen profile." >&2; exit 1; }
for img in $IMAGES; do
  echo "Checking access: $img"
  if ! docker manifest inspect "$img" >/dev/null 2>&1; then
    echo "NGC login succeeded, but this key cannot access the required image:" >&2
    echo "  $img" >&2
    echo "Provide an NGC key with access to this image's namespace, then re-run Step 1 (login) and retry." >&2
    exit 1
  fi
done

# Start all services (images pulled automatically on first run)
docker compose up -d

# Check containers are running
docker compose ps

# Read ports from the Compose environment file.
COMPOSE_ENV_BASENAME="env"
COMPOSE_ENV_FILE="$REPO_ROOT/compose/.${COMPOSE_ENV_BASENAME}"
MS_PORT=$(grep AUTO_MAGIC_CALIB_MS_PORT "$COMPOSE_ENV_FILE" | cut -d= -f2)
UI_PORT=$(grep AUTO_MAGIC_CALIB_UI_PORT "$COMPOSE_ENV_FILE" | cut -d= -f2)
HOST_IP=$(grep HOST_IP "$COMPOSE_ENV_FILE" | cut -d= -f2)

# Wait for microservice readiness. Cold image pulls or first startup can need
# extra time after `docker compose up -d` returns.
READY_URL="http://localhost:${MS_PORT}/v1/ready"
echo "Waiting for microservice readiness at ${READY_URL} ..."
ready_response=""
for attempt in $(seq 1 24); do
  if ready_response=$(curl -fsS --max-time 5 "${READY_URL}" 2>/dev/null) && \
     echo "${ready_response}" | grep -q '"code"[[:space:]]*:[[:space:]]*0'; then
    echo "Microservice ready: ${ready_response}"
    break
  fi
  if [ "${attempt}" -lt 24 ]; then
    printf "  [%02d/24] Microservice not ready yet; retrying in 5s...\n" "${attempt}"
    sleep 5
  fi
done

if ! echo "${ready_response}" | grep -q '"code"[[:space:]]*:[[:space:]]*0'; then
  echo "ERROR: microservice did not report ready within 120 seconds: ${READY_URL}" >&2
  echo "Check status and logs:" >&2
  echo "  cd ${REPO_ROOT}/compose && docker compose ps" >&2
  echo "  cd ${REPO_ROOT}/compose && docker compose logs auto-magic-calib-ms" >&2
  exit 1
fi

# Check UI is serving
UI_STATUS=$(curl -s -o /dev/null -w "%{http_code}" --max-time 5 "http://localhost:${UI_PORT}")
if [ "${UI_STATUS}" != "200" ]; then
  echo "ERROR: Web UI returned HTTP ${UI_STATUS}; check docker compose ps and UI logs." >&2
  exit 1
fi
echo "Web UI ready: HTTP ${UI_STATUS}"

echo "Microservice: http://${HOST_IP}:${MS_PORT}"
echo "Web UI:       http://${HOST_IP}:${UI_PORT}"

cd $REPO_ROOT/compose

# View logs
docker compose logs -f

# View logs for specific service
docker compose logs -f auto-magic-calib-ms

# Restart all services
docker compose restart

# Stop and remove containers
docker compose down

# Update Compose environment settings and relaunch
docker compose up -d

cd $REPO_ROOT/compose

# Stop all services (containers removed, data persisted)
docker compose down

# Stop and remove volumes
docker compose down -v