Dataset: add READMEs, organize scripts, update .gitignore

- Add README.md to all 16 dataset directories with script references
- Centralize generation scripts under scripts/ with full README
- Update .gitignore to cover all data directories, keep only metadata
- Remove redundant CCPD/.gitignore (parent covers same rules)
- Remove stale scripts/test/ (254MB pipeline residue)
- Fix label parser reference: scripts are authoritative source of truth

scripts/rebuild_spe.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python3
+"""
+批量重新生成 CCPD_SPE 数据集 — 全量版
+SPE 9类 × 8000 (ccpd_base) = 72,000 张
+蓝绿由独立脚本生成 150K+100K
+"""
+
+import os
+import sys
+import time
+from pathlib import Path
+
+ICE_DATASET = Path(r'C:\Users\Kirl\Desktop\ICEv2\ICE_Dataset')
+os.chdir(str(ICE_DATASET))
+
+sys.path.insert(0, str(ICE_DATASET / 'CCPD_SPE_GEN' / 'cv_pipeline'))
+from plate_swap import PlateSwapPipeline
+
+# 只生成 9 类特殊车牌 (蓝绿由独立脚本处理)
+SPE_TYPES = ['police','army','gangao','shiguan_old','shiguan_new',
+             'lingguan_old','lingguan_new','coach','new_energy']
+
+COUNT_PER_TYPE = 8000  # 每类 8000, 全部用 ccpd_base 背景
+
+CCPD2019_DIR = ICE_DATASET / 'CCPD' / 'CCPD2019'
+SPE_OUTPUT = ICE_DATASET / 'CCPD_SPE'
+
+SEED = 42
+WORKERS = 24
+
+def main():
+    total_start = time.time()
+    total_images = 0
+
+    import shutil
+    if SPE_OUTPUT.exists():
+        print(f"删除旧 CCPD_SPE: {SPE_OUTPUT}")
+        shutil.rmtree(str(SPE_OUTPUT))
+    SPE_OUTPUT.mkdir(parents=True, exist_ok=True)
+
+    for plate_type in SPE_TYPES:
+        print(f"\n{'='*60}")
+        print(f"[{plate_type}] {COUNT_PER_TYPE} 张")
+        print(f"{'='*60}")
+
+        pipeline = PlateSwapPipeline(plate_type=plate_type)
+        out_dir = SPE_OUTPUT / 'ccpd_base' / plate_type
+        out_dir.mkdir(parents=True, exist_ok=True)
+
+        print(f"  生成中...", end=' ', flush=True)
+        t0 = time.time()
+        pipeline.process_batch(
+            ccpd_dirs=[str(CCPD2019_DIR / 'ccpd_base')],
+            output_dir=str(out_dir),
+            num_images=COUNT_PER_TYPE,
+            preview=False,
+            seed=SEED,
+            workers=WORKERS,
+        )
+        elapsed = time.time() - t0
+        total_images += COUNT_PER_TYPE
+        print(f"完成 ({elapsed:.0f}s, {COUNT_PER_TYPE/elapsed:.0f} 张/s)")
+
+    total_t = time.time() - total_start
+    print(f"\n{'='*60}")
+    print(f"SPE 完成! {total_images} 张, {total_t/60:.1f}min")
+    print(f"{'='*60}")
+
+if __name__ == '__main__':
+    main()