#!/usr/bin/env bash
# SUM Parts - benchmark VRAM and speed of each sumv2_triangle model
#
# Uses whatever tiles are in data/sumv2_tri_texpcl. With only the demo tile
# present the per-iteration cost is still representative: voxel_max caps how
# many points reach the network per sample, so timing does not depend on how
# many tiles exist.
set -euo pipefail

CONDA_ROOT="$HOME/miniconda3"
ENV_NAME="sumparts"
SEG="$HOME/sum-parts/semantic_segmentation/PointNeXt_bundle/examples/segmentation"
SCRIPTS="/mnt/d/MYCLAUDE_PROJECT/sum-parts-test/scripts"
LOG="${LOG:-/tmp/sumparts_bench.log}"

source "$CONDA_ROOT/etc/profile.d/conda.sh"
conda activate "$ENV_NAME"
export WANDB_MODE=disabled WANDB_SILENT=true CUDA_HOME="$CONDA_PREFIX"

cd "$SEG"

set +e
python -u "$SCRIPTS/bench_models.py" "$@" > "$LOG" 2>&1
rc=$?
set -e

grep -v "it/s\]" "$LOG" | tail -40
echo "(full log: $LOG)"
exit "$rc"