#!/usr/bin/env bash
# Produce the int8 form of a model for the Hexagon (docs/dev/inference.md §5).
#
#   ./tools/quantise-models.sh PHOTO_DIR MODEL.onnx [MODEL.onnx ...]
#
# Writes `MODEL.int8.onnx` beside each input: a QDQ graph, per-channel int8
# weights, uint8 activations — the form QNN's HTP backend takes whole. The
# activations' ranges come from running the f32 model over the photographs in
# PHOTO_DIR, fed exactly as the app feeds them (letterboxed to the model's
# input, the detector's `(x - 127.5) / 128` normalisation), which is why
# this is a release-time step and not something the device does: it needs
# real photographs and, after it, a person reading §10 M2's numbers.
#
# The SCRFD and ArcFace exports are opset 11; per-channel QDQ needs 13, so a
# model below 13 is first upgraded to 17. That changes only the graph's
# spelling, not a weight — and it is what `tools/fix-face-model-shapes.sh`
# will do to the canonical files in the same model release.
#
# A venv per run, like fix-face-model-shapes.sh: the tools are not a build
# input and nothing in the tree should have them on its path.
set -euo pipefail
if [ "$#" -lt 2 ]; then
    sed -n '2,20p' "$0" >&2
    exit 2
fi
PHOTOS="$1"; shift
[ -d "${PHOTOS}" ] || { echo "no such directory: ${PHOTOS}" >&2; exit 1; }

WORK="$(mktemp -d -p /var/tmp quantise-models.XXXXXX)"
trap 'rm -rf "${WORK}"' EXIT
echo "==> venv in ${WORK}"
uv venv --python 3.12 "${WORK}/venv" >/dev/null
VIRTUAL_ENV="${WORK}/venv" uv pip install --quiet onnx onnxruntime pillow numpy sympy

exec "${WORK}/venv/bin/python" "$(dirname "$0")/quantise-models.py" "${PHOTOS}" "$@"