#!/usr/bin/env bash
# Produce the Hexagon's form of each model (docs/dev/inference.md §1.5, §5).
#
#   ./tools/quantise-models.sh PHOTO_DIR [MODEL ...]
#   ./tools/quantise-models.sh --ranges RANGES.json mosaic-hq-1408
#
# Writes `<stem>.<form>.onnx` beside each canonical file under models/: a QDQ
# graph from QNN's own quantisation config, per-channel weights, in the form
# the engine's `Rung::form` names for that role — A16W8, A16W16 or int8, each
# the narrowest that held the model's accuracy on the tablet. The activation
# ranges come from running the f32 model over the photographs in PHOTO_DIR,
# fed exactly as the app feeds them (letterbox maths, pads, normalisation,
# face crops through the app's own similarity), which is why this is a
# release-time step and not something the device does. With no MODEL, every
# model in the table.
#
# The denoiser is calibrated on noisy mosaics, not photographs: its ranges
# come from darkroom-denoise's precision gate (`--ranges`), computed on a
# smaller tile of the same network — activation ranges do not depend on the
# tile's size, and the tensor names match.
#
# Then measure before shipping: a quantised form is a different network, and
# the numbers in inference.md §1.5 are what each one had to hold.
#
# 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 1 ]; then
    sed -n '2,27p' "$0" >&2
    exit 2
fi

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 "$0")/quantise-models.py" "$@"