File size: 4,016 Bytes
9f7ad84
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
"""Train YOLOv8x on 100% of data (no validation split). For competition only."""
import sys
import torch
from pathlib import Path
from ultralytics import YOLO
import json
import shutil

_orig = torch.load
def _safe(*a, **kw): kw["weights_only"] = False; return _orig(*a, **kw)
torch.load = _safe

SEED = int(sys.argv[1]) if len(sys.argv) > 1 else 42
IMGSZ = int(sys.argv[2]) if len(sys.argv) > 2 else 1280
EPOCHS = int(sys.argv[3]) if len(sys.argv) > 3 else 100
OPTIMIZER = sys.argv[4] if len(sys.argv) > 4 else "AdamW"
LR = float(sys.argv[5]) if len(sys.argv) > 5 else 0.0005

print(f"Training: seed={SEED} imgsz={IMGSZ} epochs={EPOCHS} opt={OPTIMIZER} lr={LR}")
print("MODE: 100% training data (NO validation split)")

work_dir = Path(f"train_full_s{SEED}_i{IMGSZ}_e{EPOCHS}")
work_dir.mkdir(exist_ok=True)

ann = json.load(open("input/train/annotations.json"))
categories = ann["categories"]
images = ann["images"]
annotations = ann["annotations"]

print(f"Total images: {len(images)} (ALL used for training)")

# Use ALL images for training - copy train as val too (ultralytics requires val)
train_img_dir = work_dir / "images" / "train"
val_img_dir = work_dir / "images" / "val"
train_lbl_dir = work_dir / "labels" / "train"
val_lbl_dir = work_dir / "labels" / "val"

for d in [train_img_dir, val_img_dir, train_lbl_dir, val_lbl_dir]:
    d.mkdir(parents=True, exist_ok=True)

img_map = {img["id"]: img for img in images}
img_anns = {}
for a in annotations:
    img_anns.setdefault(a["image_id"], []).append(a)

# ALL images go to train AND val (val is just a dummy to satisfy ultralytics)
for img in images:
    src = Path("input/train/images") / img["file_name"]
    if not src.exists():
        continue

    # Symlink to train
    dst_train = train_img_dir / img["file_name"]
    if not dst_train.exists():
        shutil.copy2(src, dst_train)

    # Also copy a small subset to val (just 5 images to satisfy ultralytics)
    # We don't care about val metrics - just need it to not crash

    iw, ih = img["width"], img["height"]
    label_lines = []
    for a in img_anns.get(img["id"], []):
        x, y, w, h = a["bbox"]
        cx = (x + w / 2) / iw
        cy = (y + h / 2) / ih
        nw = w / iw
        nh = h / ih
        cx = max(0, min(1, cx))
        cy = max(0, min(1, cy))
        nw = max(0, min(1, nw))
        nh = max(0, min(1, nh))
        label_lines.append(f"{a['category_id']} {cx} {cy} {nw} {nh}")

    lbl_name = img["file_name"].rsplit(".", 1)[0] + ".txt"
    (train_lbl_dir / lbl_name).write_text("\n".join(label_lines))

# Copy first 5 images to val (dummy)
val_count = 0
for img in images[:5]:
    src = Path("input/train/images") / img["file_name"]
    dst = val_img_dir / img["file_name"]
    if src.exists() and not dst.exists():
        shutil.copy2(src, dst)
        lbl_name = img["file_name"].rsplit(".", 1)[0] + ".txt"
        lbl_src = train_lbl_dir / lbl_name
        if lbl_src.exists():
            shutil.copy2(lbl_src, val_lbl_dir / lbl_name)
        val_count += 1

nc = len(categories)
cat_names = {c["id"]: c["name"] for c in categories}
names_list = [cat_names.get(i, f"class_{i}") for i in range(nc)]

data_yaml = work_dir / "data.yaml"
data_yaml.write_text(
    f"path: {work_dir.resolve()}\n"
    f"train: images/train\n"
    f"val: images/val\n"
    f"nc: {nc}\n"
    f"names: {names_list}\n"
)

print(f"Train images: {len(images)}, Val images: {val_count} (dummy)")
print(f"Categories: {nc}")

model = YOLO("yolov8x.pt")
model.train(
    data=str(data_yaml),
    epochs=EPOCHS,
    imgsz=IMGSZ,
    batch=2 if IMGSZ <= 1280 else 1,
    workers=0,
    device=0 if torch.cuda.is_available() else "cpu",
    seed=SEED,
    close_mosaic=10,
    mosaic=1.0,
    copy_paste=0.3,
    mixup=0.2,
    degrees=10,
    translate=0.2,
    scale=0.9,
    fliplr=0.0,
    optimizer=OPTIMIZER,
    lr0=LR,
    lrf=0.01,
    warmup_epochs=5,
    cls=4.0,
    label_smoothing=0.1,
    save=True,
    save_period=25,
)

print(f"Done! Best: {work_dir}/run/weights/best.pt")