#!/usr/bin/env bash
# Foreground only. Usage: bash run_easycom_fullframe_qwen_av.sh [all|f2|f3] [seed ...]
set -euo pipefail
cd "$(dirname "$0")"

FEATURE_ROOT=${FEATURE_ROOT:-/data1/yfzx/wangx/Datasets/easycom/omni_features/open_stream_2fps_8s_last4_stack}
TARGET_ROOT=${TARGET_ROOT:-/data1/yfzx/wangx/Datasets/easycom/easycom_target_frame}
FULLFRAME_ROOT=${FULLFRAME_ROOT:-/data1/yfzx/wangx/Datasets/easycom/omni_features/fullframe_qwen_av_2fps_224}
CHECKPOINT_ROOT=${CHECKPOINT_ROOT:-checkpoints/easycom_fullframe_qwen_av}
RESULT_ROOT=${RESULT_ROOT:-results/easycom_fullframe_qwen_av}
LOCAL_PROJECTION_DIM=${LOCAL_PROJECTION_DIM:-256}
ATTENTION_DIM=${ATTENTION_DIM:-256}
ATTENTION_HEADS=${ATTENTION_HEADS:-4}
HISTORY_FRAMES=${HISTORY_FRAMES:-2}
HISTORY_MAX_GAP_SECONDS=${HISTORY_MAX_GAP_SECONDS:-0.75}
TRAIN_BATCH_SIZE=${TRAIN_BATCH_SIZE:-64}
INFER_BATCH_SIZE=${INFER_BATCH_SIZE:-128}
export OMP_NUM_THREADS=${OMP_NUM_THREADS:-4}
export MKL_NUM_THREADS=${MKL_NUM_THREADS:-4}
export OPENBLAS_NUM_THREADS=${OPENBLAS_NUM_THREADS:-4}

variant=${1:-all}
if (( $# )); then shift; fi
if (( $# )); then seeds=("$@"); else seeds=(0 1 2); fi
case "$variant" in
  all) variants=(f2 f3) ;;
  f2|f3) variants=("$variant") ;;
  *) echo "Expected all, f2, or f3" >&2; exit 2 ;;
esac

for variant in "${variants[@]}"; do
  case "$variant" in
    f2) fusion=fullframe-spatial-attention ;;
    f3) fusion=fullframe-spatiotemporal-attention ;;
  esac
  for seed in "${seeds[@]}"; do
    checkpoint="$CHECKPOINT_ROOT/${variant}_seed${seed}.pth"
    result="$RESULT_ROOT/${variant}_seed${seed}"
    if [[ -e "$checkpoint" || -e "$result" ]]; then
      echo "Refusing to overwrite $checkpoint or $result; select new output roots." >&2
      exit 1
    fi
    python train_turn_head.py \
      --feature-root "$FEATURE_ROOT" --target-root "$TARGET_ROOT" \
      --local-feature-root "$FULLFRAME_ROOT" --local-modalities av \
      --local-fusion "$fusion" \
      --local-projection-dim "$LOCAL_PROJECTION_DIM" \
      --person-attention-dim "$ATTENTION_DIM" \
      --person-attention-heads "$ATTENTION_HEADS" \
      --person-history-frames "$HISTORY_FRAMES" \
      --person-track-max-gap-seconds "$HISTORY_MAX_GAP_SECONDS" \
      --output "$checkpoint" --sessions 4 5 6 7 8 9 10 11 12 \
      --epochs 4 --batch-size "$TRAIN_BATCH_SIZE" \
      --learning-rate 7e-5 --weight-decay 5e-5 \
      --warmup-epochs 1.6 --warmup-factor 0.3 --dropout 0.2 \
      --loss lstr-mce --transition-objective none --layer-fusion concat-mlp \
      --expected-mode open-stream-replay --seed "$seed" --device cuda:0
    python infer_turn_head.py \
      --feature-root "$FEATURE_ROOT" --target-root "$TARGET_ROOT" \
      --local-feature-root "$FULLFRAME_ROOT" \
      --checkpoint "$checkpoint" --output-dir "$result" --sessions 3 2 1 \
      --batch-size "$INFER_BATCH_SIZE" \
      --expected-mode open-stream-replay --device cuda:0
  done
done