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 +1,126 @@
+"""
+CCPD原始真图 全量 TRANS (GT顶点外接框 + 12%/18%外扩)
+输出: ICE_Dataset/CCPD_REAL_TRANS/train/
+全量 ~338K, 文件名 _mask_real_ 标记 (训练时屏蔽省位+城市位)
+"""
+import os, sys, cv2, shutil
+import numpy as np
+from pathlib import Path
+
+ICEv2 = Path(r"C:\Users\Kirl\Desktop\ICEv2")
+sys.path.insert(0, str(ICEv2 / "ICE_NNv2/ICE-OCR/script/tools"))
+from dataset import parse_ccpd_filename, imread_unicode
+
+CCPD_DIRS = [
+    ICEv2 / "ICE_Dataset/CCPD/CCPD2019",
+    ICEv2 / "ICE_Dataset/CCPD/CCPD2020",
+]
+OUT_DIR = ICEv2 / "ICE_Dataset/CCPD_REAL_TRANS/train"
+EXPAND_NORMAL = 1.12
+EXPAND_SMALL  = 1.18
+SMALL_BOX_W = SMALL_BOX_H = 16
+MIN_PAD = 2
+
+
+def process_one(full_path, stem):
+    """GT顶点→外接框→12/18%外扩→裁切→顶点重映射→warp"""
+    img = imread_unicode(str(full_path))
+    if img is None:
+        return None
+    h, w = img.shape[:2]
+
+    parts = stem.split("-")
+    if len(parts) < 4:
+        return None
+    # GT顶点 (CCPD: br, bl, tl, tr)
+    verts = []
+    for v in parts[3].split("_"):
+        x, y = v.split("&")
+        verts.append([float(x), float(y)])
+    verts = np.float32(verts)
+
+    # 外接框
+    x1, y1 = verts[:, 0].min(), verts[:, 1].min()
+    x2, y2 = verts[:, 0].max(), verts[:, 1].max()
+    bw, bh = x2 - x1, y2 - y1
+
+    # 外扩
+    ef = EXPAND_SMALL if (bw < SMALL_BOX_W or bh < SMALL_BOX_H) else EXPAND_NORMAL
+    px = max(MIN_PAD, int(round(bw * (ef - 1.0) / 2.0)))
+    py = max(MIN_PAD, int(round(bh * (ef - 1.0) / 2.0)))
+    cx1 = max(0, int(x1) - px); cy1 = max(0, int(y1) - py)
+    cx2 = min(w, int(x2) + px); cy2 = min(h, int(y2) + py)
+    if cx2 <= cx1 or cy2 <= cy1:
+        return None
+
+    cropped = img[cy1:cy2, cx1:cx2]
+
+    # 顶点重映射到裁切坐标 + OpenCV顺序 (CCPD: br,bl,tl,tr → tl,tr,br,bl)
+    verts_crop = verts[[2, 3, 0, 1], :] - np.array([cx1, cy1])
+    verts_crop = verts_crop.astype(np.float32)
+
+    OW, OH = 192, 64
+    dst = np.float32([[0, 0], [OW - 1, 0], [OW - 1, OH - 1], [0, OH - 1]])
+    M = cv2.getPerspectiveTransform(verts_crop, dst)
+    return cv2.warpPerspective(cropped, M, (OW, OH))
+
+
+if __name__ == "__main__":
+    # Step 0: 清空
+    if OUT_DIR.exists():
+        shutil.rmtree(str(OUT_DIR))
+    OUT_DIR.mkdir(parents=True, exist_ok=True)
+
+    # Step 1: 收集
+    print("[1/2] Scanning all CCPD...")
+    all_files = []
+    total = skipped = 0
+    for d in CCPD_DIRS:
+        for root, dirs, files in os.walk(str(d)):
+            for f in files:
+                if not f.lower().endswith(".jpg"):
+                    continue
+                indices, plate = parse_ccpd_filename(f)
+                if indices is None:
+                    skipped += 1
+                    continue
+                total += 1
+                all_files.append((os.path.join(root, f), Path(f).stem, plate))
+
+    print(f"  Valid: {total}, Skipped: {skipped}")
+    for prov in sorted(set(p[2][0] for p in all_files),
+                       key=lambda p: -sum(1 for x in all_files if x[2][0] == p)):
+        cnt = sum(1 for x in all_files if x[2][0] == prov)
+        print(f"    {prov}: {cnt}")
+
+    # Step 2: GT顶点 warp
+    print(f"\n[2/2] GT-vertex warp {len(all_files)} -> {OUT_DIR}...")
+    done = err = 0
+    for i, (full_path, stem, plate) in enumerate(all_files):
+        try:
+            warped = process_one(full_path, stem)
+            if warped is None:
+                err += 1
+                continue
+
+            # _mask_real_ 标记: 训练时屏蔽 pos0(省)+pos1(城市码)
+            out_name = f"{stem}_mask_real_{plate}_trans.jpg"
+            out_path = OUT_DIR / out_name
+
+            ret, enc = cv2.imencode(".jpg", warped, [cv2.IMWRITE_JPEG_QUALITY, 95])
+            if ret:
+                with open(str(out_path), "wb") as wf:
+                    wf.write(enc.tobytes())
+                done += 1
+            else:
+                err += 1
+        except Exception as e:
+            err += 1
+            if err <= 3:
+                print(f"  [!] {Path(full_path).name}: {e}")
+
+        if (i + 1) % 10000 == 0:
+            print(f"  [{i+1}/{len(all_files)}] done={done}, err={err}")
+
+    print(f"\nDone! Saved: {done}, Errors: {err}")
+    print(f"Output: {OUT_DIR} ({len(list(OUT_DIR.glob('*.jpg')))} files)")