dtourolle
2bf0ec8dba
tools/onnx-probe-on-device.sh cross-builds dr-segment's onnx_probe without the embedded segmentation model, pushes it with a model to the attached device and times two runs. The 768×1024 XFeat export takes ~400 ms on the reference tablet's NEON cores against ~300 ms on the desktop, with identical output ranges — inside NFR-MRG-1's 1 s per frame. The blend half of S15.4 waits for a chunked blend to exist.
61 lines
2.4 KiB
Bash
Executable File
61 lines
2.4 KiB
Bash
Executable File
#!/usr/bin/env bash
|
||
# Time an ONNX model under tract on a connected Android device.
|
||
#
|
||
# ./tools/onnx-probe-on-device.sh models/keypoints/xfeat-1024.onnx [1x1x768x1024]
|
||
#
|
||
# ## Why this exists
|
||
#
|
||
# Every model the app runs on the CPU — faces, masks, keypoints — runs under
|
||
# tract on NEON when it runs on the tablet, and the desktop figure says
|
||
# nothing about that: twenty cores of AVX2 against a tablet's big.LITTLE
|
||
# cluster is not a ratio anyone should guess (faces.md §9 measured 2×
|
||
# on one workload and would have guessed wrong). NFR-MRG-1 puts a per-frame
|
||
# budget on keypoint detection *on the tablet*, and this is how the number
|
||
# is measured rather than assumed.
|
||
#
|
||
# Cross-builds `dr-segment`'s `onnx_probe` example — without the embedded
|
||
# segmentation model, which the probe does not need and which is 11 MB the
|
||
# push would otherwise carry — pushes it with the model to `/data/local/tmp`,
|
||
# runs it twice (tract's first run pays for planning) and removes both.
|
||
#
|
||
# Not part of CI, which has no device attached.
|
||
set -euo pipefail
|
||
|
||
TARGET=aarch64-linux-android
|
||
API=26
|
||
DEST=/data/local/tmp
|
||
|
||
MODEL="${1:?usage: onnx-probe-on-device.sh <model.onnx> [NxCxHxW]}"
|
||
SHAPE="${2:-1x1x768x1024}"
|
||
|
||
ndk="${ANDROID_NDK_HOME:-}"
|
||
if [[ -z "$ndk" ]]; then
|
||
ndk=$(find "${ANDROID_HOME:-$HOME/Android/Sdk}/ndk" -maxdepth 1 -mindepth 1 -type d 2>/dev/null |
|
||
sort -V | tail -1)
|
||
fi
|
||
clang="$ndk/toolchains/llvm/prebuilt/linux-x86_64/bin/$TARGET$API-clang"
|
||
[[ -x "$clang" ]] || {
|
||
echo "no $TARGET$API-clang in $ndk — set ANDROID_NDK_HOME" >&2
|
||
exit 1
|
||
}
|
||
rustup target list --installed | grep -qx "$TARGET" || rustup target add "$TARGET"
|
||
|
||
adb devices | grep -qw device || {
|
||
echo "no device attached — plug the tablet in and enable USB debugging" >&2
|
||
exit 1
|
||
}
|
||
|
||
echo "building onnx_probe for $TARGET…"
|
||
CARGO_TARGET_AARCH64_LINUX_ANDROID_LINKER="$clang" \
|
||
CC_aarch64_linux_android="$clang" \
|
||
cargo build -q -p dr-segment --example onnx_probe --release --target "$TARGET" \
|
||
--no-default-features --features semantic
|
||
binary="${CARGO_TARGET_DIR:-target}/$TARGET/release/examples/onnx_probe"
|
||
|
||
echo "pushing $(basename "$binary") and $(basename "$MODEL")…"
|
||
adb push "$binary" "$DEST/onnx_probe" >/dev/null
|
||
adb push "$MODEL" "$DEST/probe.onnx" >/dev/null
|
||
adb shell chmod 755 "$DEST/onnx_probe"
|
||
adb shell "$DEST/onnx_probe" "$DEST/probe.onnx" "$SHAPE"
|
||
adb shell rm -f "$DEST/onnx_probe" "$DEST/probe.onnx"
|