dtourolle
0e6ac09fd5
tools/quantise-models.sh now writes each model's Hexagon form from a per-model table: the form its role takes on the NPU (int8, A16W8 or A16W16), the exact graph rewrites it needs, and the nodes that must stay float. Ranges are min/max over photographs fed exactly as the app feeds each model -- the detector and segmenter letterboxes with their own pads and normalisation, landmark crops from the detector's boxes, MI-GAN with a panorama-like border, XFeat's grey proxy. The old tool used an antialiased resize, YOLO's pad of 128 and /255 for every model that was not a face model, none of which is what the app does. tools/htp_graph.py holds the rewrites, each checked against the input graph before use: the denoiser's 6-D Bayer pack and XFeat's 224-slice unfold as SpaceToDepth (QNN stops at rank 5), computed reshape targets folded, and bilinear Resize as two MatMuls (the HTP refuses ResizeBilinear at XFeat's sizes). The denoiser takes ranges computed by darkroom-denoise's gate on a smaller tile of the same network.
40 lines
1.8 KiB
Bash
Executable File
40 lines
1.8 KiB
Bash
Executable File
#!/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-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 "$0")/quantise-models.py" "$@"
|