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
2026-06-23 14:41:39 +08:00
1 parent 7867c3bfaf
commit a64690477a
@@ -0,0 +1,99 @@
+#!/usr/bin/env python3
+"""
+C++ 管线批量重生 CCPD_SPE (9 类 x 7 子集 = 9,000 张)
+比 Python 版快 ~5x，24 线程饱和
+"""
+
+import os
+import sys
+import time
+import shutil
+import subprocess
+from pathlib import Path
+
+ICE_DATASET = Path(r'C:\Users\Kirl\Desktop\ICEv2\ICE_Dataset')
+CPP_EXE = ICE_DATASET / 'CCPD_SPE_GEN' / 'cpp_pipeline' / 'build' / 'Release' / 'plate_swap.exe'
+PLATE_POOL = ICE_DATASET / 'cpp_pipeline' / 'output' / 'plate_pool'
+CCPD2019 = ICE_DATASET / 'CCPD' / 'CCPD2019'
+SPE_OUT = ICE_DATASET / 'CCPD_SPE'
+
+# 原始分布
+DIST = {
+    'ccpd_base':      588,
+    'ccpd_blur':       55,
+    'ccpd_challenge': 159,
+    'ccpd_fn':         58,
+    'ccpd_rotate':     30,
+    'ccpd_tilt':       82,
+    'ccpd_weather':    28,
+}
+
+TYPES = ['police','army','gangao','shiguan_old','shiguan_new',
+         'lingguan_old','lingguan_new','coach','new_energy']
+
+WORKERS = 24  # 物理核心数
+SEED = 42
+
+def main():
+    if not CPP_EXE.exists():
+        print(f"[FATAL] C++ exe not found: {CPP_EXE}")
+        return 1
+    if not PLATE_POOL.is_dir():
+        print(f"[FATAL] Plate pool not found: {PLATE_POOL}")
+        return 1
+
+    # 清空旧数据
+    if SPE_OUT.exists():
+        print(f"删除旧 CCPD_SPE: {SPE_OUT}")
+        shutil.rmtree(str(SPE_OUT))
+
+    total_start = time.time()
+    total = 0
+
+    for plate_type in TYPES:
+        t0 = time.time()
+        type_count = 0
+        print(f"\n{'='*50}")
+        print(f"[{plate_type}]")
+        print(f"{'='*50}")
+
+        for subdir, count in DIST.items():
+            ccpd_dir = CCPD2019 / subdir
+            if not ccpd_dir.is_dir():
+                continue
+
+            out_dir = SPE_OUT / subdir / plate_type
+            out_dir.mkdir(parents=True, exist_ok=True)
+
+            cmd = [
+                str(CPP_EXE),
+                '--ccpd-dir', str(ccpd_dir),
+                '--plate-type', plate_type,
+                '--plate-pool', str(PLATE_POOL),
+                '--output', str(out_dir),
+                '--num', str(count),
+                '--workers', str(WORKERS),
+                '--seed', str(SEED + hash(plate_type) % 10000),
+            ]
+
+            print(f"  {subdir}: {count} 张...", end=' ', flush=True)
+            result = subprocess.run(cmd, capture_output=True, text=True)
+            if result.returncode == 0:
+                print(f"OK")
+                type_count += count
+            else:
+                print(f"FAIL")
+                print(f"    stderr: {result.stderr[:200]}")
+
+        elapsed = time.time() - t0
+        print(f"  [{plate_type}] {type_count} 张, {elapsed:.0f}s")
+        total += type_count
+
+    total_t = time.time() - total_start
+    print(f"\n{'='*50}")
+    print(f"DONE! {total} 张, {total_t/60:.1f}min")
+    print(f"{'='*50}")
+
+if __name__ == '__main__':
+    os.chdir(str(ICE_DATASET))
+    main()