phase 1

pipeline/orchestrator.sh

@@ -0,0 +1,36 @@
+#!/bin/bash
+SAMPLE_DIR=${1:-"sample"}
+TRAIN_DIR="$SAMPLE_DIR/training"
+VAL_DIR="$SAMPLE_DIR/validation"
+MODEL_DIR="$SAMPLE_DIR/model"
+DATA_DIR="$SAMPLE_DIR/dataset"
+EPOCHS=50
+
+while true; do
+    echo "--- [준비] 폴더 초기화 ---"
+    rm -rf "$TRAIN_DIR" "$VAL_DIR" "$DATA_DIR" "sample/output/factorize"
+    mkdir -p "$TRAIN_DIR" "$VAL_DIR" "$MODEL_DIR" "$DATA_DIR" "sample/output/factorize" "sample/output"
+
+    echo "--- [채보 선별] ---"
+    find tja -name "*.tja" | sort -R > file_list.txt
+    head -n 200 file_list.txt | xargs -I {} cp {} "$TRAIN_DIR/"
+    tail -n 50 file_list.txt | xargs -I {} cp {} "$VAL_DIR/"
+
+    echo "--- [학습 진행] Epoch: $EPOCHS ---"
+    ./scripts/run_train.sh "$TRAIN_DIR" "$MODEL_DIR" "$DATA_DIR" "$EPOCHS"
+    
+    echo "--- [검증 및 상수 추론] ---"
+    bun run scripts/predict_batch.ts "$MODEL_DIR" "$SAMPLE_DIR"
+    bun run scripts/compare_results.ts "$SAMPLE_DIR"
+
+    # 오차 검사
+    high_error=$(jq 'map(select(.diff != null and (.diff | tonumber | fabs > 0.1))) | length' "$SAMPLE_DIR/comparison.json")
+
+    if [ "$high_error" -eq 0 ]; then
+        echo "목표 달성: 모든 예측 오차가 0.1 이내입니다."
+        break
+    else
+        echo "오차 발생: $high_error 건이 0.1 초과. 학습 강도(Epoch)를 2배로 늘려 재학습합니다."
+        EPOCHS=$((EPOCHS * 2))
+    fi
+done