#!/usr/bin/env bash
# Step1 pretrain — 합성 데이터로 PGNet 학습
#
# 컨테이너 안 실행:
#   docker exec kr_lp_pgnet bash /workspace/kr_lp_pgnet/scripts/run_step1.sh
#
# 환경 변수:
#   DRY_RUN=1   2 epoch만 돌려 동작 검증
#   EPOCHS=N    epoch 수 override (기본 config의 epoch_num)
#   LOG=path    로그 파일 (기본: /workspace/PaddleOCR/output/kr_lp_pgnet/train.log)

set -euo pipefail

PADDLEOCR_DIR=/workspace/PaddleOCR
KR_LP_DIR=/workspace/kr_lp_pgnet
TRAIN_DATA=/workspace/train_data
LOG="${LOG:-$PADDLEOCR_DIR/output/kr_lp_pgnet/train.log}"

cd "$PADDLEOCR_DIR"

# train_data symlink (config는 ./train_data/kr_lp_synth 사용)
if [ ! -e ./train_data ]; then
    ln -sf "$TRAIN_DATA" ./train_data
fi

mkdir -p "$(dirname "$LOG")"

OVERRIDE=(
    -o Global.pretrained_model=./pretrain_models/train_step1/best_accuracy
       Global.load_static_weights=False
)
if [ -n "${EPOCHS:-}" ]; then
    OVERRIDE+=(Global.epoch_num="$EPOCHS")
fi
if [ "${DRY_RUN:-0}" = "1" ]; then
    OVERRIDE+=(Global.epoch_num=2 Global.eval_batch_step="[0,200]")
    echo "DRY_RUN=1 → 2 epoch만 실행"
fi

echo "==========================="
echo "Step1 학습 시작"
echo "  config:  configs/e2e/kr_lp_pgnet.yml"
echo "  data:    $TRAIN_DATA/kr_lp_synth/"
echo "  pretrain: pretrain_models/train_step1/best_accuracy"
echo "  log:     $LOG"
echo "  override: ${OVERRIDE[@]}"
echo "==========================="

python3.10 tools/train.py -c configs/e2e/kr_lp_pgnet.yml "${OVERRIDE[@]}" 2>&1 | tee "$LOG"