Add 80/20 random split (replaces cross-area 46/54 split)

- scripts/make_split.py: merges cross-area train+test (33,708 pairs),
  shuffles with seed=42, splits 80/20
- meta/train_80.json (26,966) + meta/test_20.json (6,742)
- After seg filter: 24,891 train / 6,252 test
- Default paths in train_gtauav.py updated to use new split

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

CLAUDE.md

@@ -158,8 +158,10 @@ Meta-файл `meta/seg_filter.json`: исключение изображени
   - Drone: RandomResizedCrop(0.7-1.0), HFlip, Rotation(15°), ColorJitter, Grayscale(5%), GaussianBlur
   - Satellite: RandomResizedCrop(0.7-1.0), HFlip, ColorJitter, Grayscale(5%)
   - Eval: Resize+CenterCrop (clean, no augmentation)
-- Train: 15,693 pairs → 13,622 after seg filter (cross-area)
+- **Split:** 80/20 random из всех 33,708 пар (`meta/train_80.json` / `meta/test_20.json`)
-- Test: 18,015 pairs
+- Train: 26,966 → 24,891 after seg filter
+- Test: 6,742 → 6,252 after seg filter
+- Скрипт: `python -m scripts.make_split --ratio 0.8 --seed 42`
 
 ### V2 (UAV-GeoLoc, gin)
 | Конфиг | Gate init | Описание |

README.md

@@ -29,7 +29,7 @@ Loss:    InfoNCE(query, gallery)
 - Captions: `/home/servml/Документы/datasets/GTA-UAV-LR-captions/` (40K JSON, 3-paragraph VLM)
 - Segmentation: `/home/servml/Документы/datasets/GTA-UAV-LR-aug/` (17 classes)
 - Seg filter: 37,498 passed / 10,905 excluded (>=90% background+water)
-- Train: 15,693 pairs, Test: 18,015 pairs (cross-area split)
+- Split: 80/20 random (26,966 train / 6,742 test → 24,891/6,252 after seg filter)
 
 ### V2 — UAV-GeoLoc + GeoRSCLIP (legacy)
 
@@ -89,9 +89,10 @@ numpy
 
 ## Workflow (V3 — GTA-UAV)
 
-### 1. Filter segmentation (exclude uninformative images)
+### 1. Create 80/20 split and filter segmentation
 
 ```bash
+python -m scripts.make_split --output-dir meta
 python -m scripts.filter_segmentation --output meta/seg_filter.json
 ```
 

scripts/make_split.py

@@ -0,0 +1,87 @@
+from __future__ import annotations
+
+"""Create 80/20 train/test split from GTA-UAV-LR pair JSONs.
+
+Merges cross-area train+test (33,708 pairs), shuffles deterministically,
+and saves new 80/20 split JSONs.
+
+Usage:
+    python -m scripts.make_split [--ratio 0.8] [--seed 42]
+"""
+
+import argparse
+import json
+import logging
+import random
+from pathlib import Path
+
+import coloredlogs
+
+LOGGER = logging.getLogger("caption_test.make_split")
+
+_RGB_ROOT = Path("/home/servml/Документы/datasets/GTA-UAV-LR")
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(description="Create 80/20 split for GTA-UAV-LR.")
+    parser.add_argument("--ratio", type=float, default=0.8, help="Train ratio (default 0.8).")
+    parser.add_argument("--seed", type=int, default=42, help="Random seed.")
+    parser.add_argument(
+        "--output-dir", type=str, default="meta",
+        help="Output directory for split JSONs.",
+    )
+    args = parser.parse_args()
+
+    coloredlogs.install(
+        level="INFO", logger=LOGGER,
+        fmt="%(asctime)s %(name)s %(levelname)s %(message)s",
+    )
+
+    # Load both original splits.
+    train_path = _RGB_ROOT / "cross-area-drone2sate-train.json"
+    test_path = _RGB_ROOT / "cross-area-drone2sate-test.json"
+
+    LOGGER.info("📂 Loading %s", train_path.name)
+    with open(train_path) as f:
+        part1 = json.load(f)
+    LOGGER.info("📂 Loading %s", test_path.name)
+    with open(test_path) as f:
+        part2 = json.load(f)
+
+    all_pairs = part1 + part2
+    LOGGER.info("📊 Total pairs: %d", len(all_pairs))
+
+    # Shuffle deterministically.
+    rng = random.Random(args.seed)
+    rng.shuffle(all_pairs)
+
+    # Split.
+    n_train = int(len(all_pairs) * args.ratio)
+    train_pairs = all_pairs[:n_train]
+    test_pairs = all_pairs[n_train:]
+
+    LOGGER.info(
+        "✂️  Split %.0f/%.0f: train=%d (%.1f%%)  test=%d (%.1f%%)",
+        args.ratio * 100, (1 - args.ratio) * 100,
+        len(train_pairs), 100 * len(train_pairs) / len(all_pairs),
+        len(test_pairs), 100 * len(test_pairs) / len(all_pairs),
+    )
+
+    # Save.
+    out_dir = Path(args.output_dir)
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    train_out = out_dir / "train_80.json"
+    test_out = out_dir / "test_20.json"
+
+    with train_out.open("w", encoding="utf-8") as f:
+        json.dump(train_pairs, f)
+    with test_out.open("w", encoding="utf-8") as f:
+        json.dump(test_pairs, f)
+
+    LOGGER.info("💾 Saved: %s (%d pairs)", train_out, len(train_pairs))
+    LOGGER.info("💾 Saved: %s (%d pairs)", test_out, len(test_pairs))
+
+
+if __name__ == "__main__":
+    main()

src/training/train_gtauav.py

@@ -37,8 +37,8 @@ LOGGER = logging.getLogger("caption_test.train_gtauav")
 # Default paths.
 _RGB_ROOT = "/home/servml/Документы/datasets/GTA-UAV-LR"
 _CAPTION_ROOT = "/home/servml/Документы/datasets/GTA-UAV-LR-captions"
-_TRAIN_JSON = f"{_RGB_ROOT}/cross-area-drone2sate-train.json"
+_TRAIN_JSON = "meta/train_80.json"
-_TEST_JSON = f"{_RGB_ROOT}/cross-area-drone2sate-test.json"
+_TEST_JSON = "meta/test_20.json"
 
 _DINO_WEB = "nn_models/DINO_WEB/dinov3-vitl16-pretrain-lvd1689m.pth"
 _DINO_SAT = "nn_models/DINO_SAT/model.safetensors"