#!/usr/bin/env bash
# SUM Parts - score the trained model on the classes this project actually needs
#
# Runs the sliding-window test() path over the VAL split (which has real labels,
# unlike the blind test split), then re-scores the predictions after merging
# SUM's 13 fine classes down to building / vegetation / vehicle / ground.
set -uo pipefail

CONDA_ROOT="$HOME/miniconda3"
SEG="$HOME/sum-parts/semantic_segmentation/PointNeXt_bundle/examples/segmentation"
DATA="$HOME/sum-parts/data/face_labeling/texsp_pcl"
SCRIPTS="/mnt/d/MYCLAUDE_PROJECT/sum-parts-test/scripts"
OUT="$HOME/sum-parts/runs/coarse_eval"

source "$CONDA_ROOT/etc/profile.d/conda.sh"
conda activate sumparts
export WANDB_MODE=disabled WANDB_SILENT=true CUDA_HOME="$CONDA_PREFIX"
export PYTORCH_CUDA_ALLOC_CONF="garbage_collection_threshold:0.7,max_split_size_mb:128"

mkdir -p "$OUT"
cd "$SEG"

CKPT=$(find "$SEG/log/sumv2_triangle" -name '*_ckpt_best.pth' -printf '%T@ %p\n' \
       | sort -rn | head -1 | cut -d' ' -f2-)
echo "checkpoint: $(basename "$CKPT")"

# test() writes prediction plys and slides over whole tiles; point it at val so
# there is ground truth to score against.
#
# TEST_VOXEL_MAX matters more than it looks. PointNet max-pools ONE global
# feature over whatever it is handed, so the number of points per forward pass
# is part of the model's operating point, not a neutral batching knob. Training
# used 64000-point crops; the cfg's test default (null) feeds ~350k-point chunks
# and the predictions collapse toward the majority class. Set it to 64000 to
# make inference match training.
TEST_VOXEL_MAX="${TEST_VOXEL_MAX:-}"
VM_ARG=()
[ -n "$TEST_VOXEL_MAX" ] && VM_ARG=(dataset.test.voxel_max="$TEST_VOXEL_MAX")

echo "=== inference over val split (sliding window) ==="
echo "    test voxel_max: ${TEST_VOXEL_MAX:-null (cfg default)}"
python -u main.py \
    --cfg ../../cfgs/sumv2_triangle/pointnet.yaml \
    mode=test \
    --pretrained_path "$CKPT" \
    dataset.common.data_root="$DATA" \
    dataset.test.split=val \
    "${VM_ARG[@]}" \
    wandb.use_wandb=False \
    > "$OUT/infer.log" 2>&1
rc=$?
if [ $rc -ne 0 ]; then
    echo "  FAILED rc=$rc"
    tail -15 "$OUT/infer.log"
    exit $rc
fi
grep -aE 'test_oa|iou per cls' "$OUT/infer.log" | tail -4

VIS=$(dirname "$(dirname "$CKPT")")/visualization
echo
echo "=== predictions in $VIS ==="
ls -1 "$VIS" | grep -c '_pred.ply' || true

echo
echo "=== re-scoring at project granularity ==="
python "$SCRIPTS/coarse_eval.py" --pred-dir "$VIS" --gt-dir "$DATA/val" \
    | tee "$OUT/coarse.txt"

echo
echo "logs in $OUT"