feat(detect): 按来源类别处置无框图片(--empty-policy)
空标签在 YOLO 里的语义是"这张图什么都没有",是一个明确的负样本断言,而不是 "有缺陷但没能定位出来"。原先一律保留,于是 runs/boxes_gradcam 的 339 张空标签 里有 270 张是人工标成缺陷、Grad-CAM 却失手的图(blackdot 占该类 11%、black 占 24%),它们正以"此图无缺陷"的身份进入训练,等于在教模型抑制真实缺陷。 --empty-policy 接一个全局默认加若干 `类别=策略`: keep 当负样本保留(默认)/ drop 丢弃 / full 退化成整图框 整图框需要重写标签而不是链接源文件(内容不同),且有了确定类别之后要跟着本类 一起参与分层划分。类别名或策略拼错直接报错——静默忽略会让策略看着生效其实没有。 没显式指定、又落到 keep 的类别会打一条告警。 替换掉原来的 --drop-empty:它是一刀切,会把 normal 那 69 张有价值的负样本一起扔掉。 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
co-authored by
Claude Opus 5
parent
d6c6aca325
commit
012b3efc73
@@ -621,8 +621,38 @@ data/boxes_gradcam/
|
||||
按类别分层(`--val-ratio` 默认 0.2,`--seed` 默认 42,两次运行结果一致)。分层是必需的:
|
||||
`black` 只有 53 张、`others` 69 张,随机切很容易让某个小类在验证集里挂零,指标就成了空的。
|
||||
|
||||
无框的图(Grad-CAM 没框出东西的那 339 张,占 3%)**默认保留**——在检测训练里它们是负样本,
|
||||
对压低误检有用。不要时加 `--drop-empty`。
|
||||
### 没有框的图怎么处理
|
||||
|
||||
Grad-CAM 没框出东西的有 339 张(占 3%)。它们**默认保留为负样本**,对压低误检有用。
|
||||
|
||||
但要当心:**空标签在 YOLO 里的语义是"这张图什么都没有"**——一个明确的负样本断言,
|
||||
而不是"有缺陷但没能定位出来"。而这 339 张里只有 69 张真的来自 `normal`,其余 270 张是人工
|
||||
标成缺陷、Grad-CAM 却失手的图:
|
||||
|
||||
| 来源类别 | 空标签 | 占该类 |
|
||||
|---|---|---|
|
||||
| grease | 95 | 7.8% |
|
||||
| blackdot | 82 | 11.3% |
|
||||
| normal | 69 | 2.6% |
|
||||
| strip_h | 28 | 2.9% |
|
||||
| zigzag | 23 | 2.4% |
|
||||
| black | 17 | 24.3% |
|
||||
| 其余 9 类 | 25 | <3% |
|
||||
|
||||
照搬的话,`blackdot` 有 11% 的正样本、`black` 有 24% 会以"此图无缺陷"的身份进入训练,
|
||||
等于在教模型抑制真实缺陷。用 `--empty-policy` 按来源类别分别处置:
|
||||
|
||||
```bash
|
||||
uv run python scripts/prepare_yolo_dataset.py --source runs/boxes_gradcam \
|
||||
--empty-policy drop normal=keep black=full edge_clean=full
|
||||
```
|
||||
|
||||
- `keep`(默认)——当负样本保留。只有真正无缺陷的类别该用
|
||||
- `drop`——丢弃。缺陷类没定位出来的属于**信息缺失**,不该冒充负样本
|
||||
- `full`——退化成整图框。适合 `black`/`edge_clean` 这种描述整图属性、缺陷本就铺满全图的类别
|
||||
|
||||
第一个裸词是全局默认,后面 `类别=策略` 逐类覆盖。类别名或策略写错会直接报错而不是静默忽略。
|
||||
没有显式指定策略、又落到 `keep` 的类别会打一条告警,提醒你确认它是否真的无缺陷。
|
||||
|
||||
拍平之后不同类别目录下的同名文件会互相覆盖,脚本会直接报错而不是静默丢数据;
|
||||
真遇上就用 `scripts/export_clusters.py --prefix-parent` 重新导出。
|
||||
|
||||
+162
-26
@@ -25,7 +25,12 @@ data/<name>/
|
||||
└── data.yaml
|
||||
```
|
||||
|
||||
没有框的图(标签为空)默认保留:YOLO 训练里它们是负样本,有助于压低误检。
|
||||
没有框的图(标签为空)默认保留:YOLO 训练里它们是负样本,有助于压低误检。但**空标签的
|
||||
语义是"这张图什么都没有"**,不是"有缺陷但没定位出来"。来自缺陷类别的空标签如果照搬,
|
||||
等于在教模型抑制真实缺陷,所以可以用 `--empty-policy` 按来源类别分别处置:
|
||||
|
||||
--empty-policy drop normal=keep black=full
|
||||
# 缺陷类没定位出来的直接丢弃;normal 留作负样本;整图属性的类退化成整图框
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
@@ -38,7 +43,9 @@ import random
|
||||
import shutil
|
||||
import sys
|
||||
from collections import Counter, defaultdict
|
||||
from collections.abc import Sequence
|
||||
from pathlib import Path
|
||||
from typing import NamedTuple
|
||||
|
||||
sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
|
||||
|
||||
@@ -49,6 +56,13 @@ from utils import setup_logging # noqa: E402
|
||||
|
||||
logger = None
|
||||
|
||||
EMPTY_POLICIES = ("keep", "drop", "full")
|
||||
EMPTY_POLICY_DESC = {
|
||||
"keep": "保留为负样本",
|
||||
"drop": "丢弃",
|
||||
"full": "退化成整图框",
|
||||
}
|
||||
|
||||
|
||||
def link_or_copy(source: Path, destination: Path) -> str:
|
||||
"""硬链接;跨文件系统时退回复制。"""
|
||||
@@ -65,6 +79,25 @@ def link_or_copy(source: Path, destination: Path) -> str:
|
||||
return "copy"
|
||||
|
||||
|
||||
class Sample(NamedTuple):
|
||||
"""一张图及其标签。
|
||||
|
||||
Attributes:
|
||||
image: 图片路径。
|
||||
label: 标签路径。
|
||||
class_id: 标签里第一个框的类别下标;无框时为 None。
|
||||
group: 来源的类别目录名——也就是人工归类给这张图的类别。
|
||||
标签为空时,这是唯一还能知道"这张图本该是什么"的线索。
|
||||
full_box: 整图框的类别下标。非 None 时 _emit 会**重写**标签而不是链接原文件。
|
||||
"""
|
||||
|
||||
image: Path
|
||||
label: Path
|
||||
class_id: int | None
|
||||
group: str
|
||||
full_box: int | None = None
|
||||
|
||||
|
||||
def first_class_id(label_path: Path) -> int | None:
|
||||
"""取标签里第一个框的类别下标;空标签(无框)返回 None。"""
|
||||
for line in label_path.read_text(encoding="utf-8").splitlines():
|
||||
@@ -74,28 +107,92 @@ def first_class_id(label_path: Path) -> int | None:
|
||||
return None
|
||||
|
||||
|
||||
def collect(source: Path) -> list[tuple[Path, Path, int | None]]:
|
||||
"""配对 images/ 与 labels/,返回 (图片, 标签, 类别下标) 列表。"""
|
||||
def collect(source: Path) -> list[Sample]:
|
||||
"""配对 images/ 与 labels/。"""
|
||||
images_root, labels_root = source / "images", source / "labels"
|
||||
if not images_root.is_dir() or not labels_root.is_dir():
|
||||
raise FileNotFoundError(f"{source} 下缺少 images/ 或 labels/,先跑 scripts/generate_boxes.py")
|
||||
|
||||
pairs = []
|
||||
samples = []
|
||||
missing = []
|
||||
for image in sorted(p for p in images_root.rglob("*") if p.suffix.lower() in IMAGE_SUFFIXES):
|
||||
label = labels_root / image.relative_to(images_root).with_suffix(".txt")
|
||||
relative = image.relative_to(images_root)
|
||||
label = labels_root / relative.with_suffix(".txt")
|
||||
if not label.exists():
|
||||
missing.append(image)
|
||||
continue
|
||||
pairs.append((image, label, first_class_id(label)))
|
||||
group = relative.parent.name # 顶层就是图片时为 ""
|
||||
samples.append(Sample(image, label, first_class_id(label), group))
|
||||
if missing:
|
||||
raise FileNotFoundError(
|
||||
f"有 {len(missing)} 张图没有对应的标签,例如 {missing[0]};"
|
||||
"产出目录可能不完整,重新跑一次 generate_boxes.py"
|
||||
)
|
||||
if not pairs:
|
||||
if not samples:
|
||||
raise ValueError(f"{source} 下没有找到任何图片")
|
||||
return pairs
|
||||
return samples
|
||||
|
||||
|
||||
def parse_empty_policy(tokens: Sequence[str]) -> tuple[str, dict[str, str]]:
|
||||
"""解析 --empty-policy:一个可选的全局默认,加若干 `类别=策略`。
|
||||
|
||||
--empty-policy drop normal=keep black=full
|
||||
-> ("drop", {"normal": "keep", "black": "full"})
|
||||
"""
|
||||
default, per_class = "keep", {}
|
||||
for token in tokens:
|
||||
if "=" in token:
|
||||
name, _, policy = token.partition("=")
|
||||
if policy not in EMPTY_POLICIES:
|
||||
raise ValueError(f"未知策略 {policy!r}(类别 {name});可选 {EMPTY_POLICIES}")
|
||||
per_class[name] = policy
|
||||
elif token in EMPTY_POLICIES:
|
||||
default = token
|
||||
else:
|
||||
raise ValueError(
|
||||
f"看不懂 --empty-policy 的 {token!r};"
|
||||
f"要么是全局默认({'/'.join(EMPTY_POLICIES)}),要么是 `类别=策略`"
|
||||
)
|
||||
return default, per_class
|
||||
|
||||
|
||||
def apply_empty_policy(
|
||||
samples: Sequence[Sample], default: str, per_class: dict[str, str], names: Sequence[str]
|
||||
) -> tuple[list[Sample], dict[str, tuple[str, int]]]:
|
||||
"""按来源类别处置空标签,返回 (保留下来的样本, {类别: (策略, 数量)})。
|
||||
|
||||
空标签在 YOLO 里的语义是"这张图什么都没有"——一个明确的负样本断言,而不是
|
||||
"有缺陷但没定位出来"。所以来自缺陷类别的空标签如果照搬,等于在教模型抑制真实缺陷。
|
||||
"""
|
||||
index = {name: i for i, name in enumerate(names)}
|
||||
unknown = {
|
||||
name for name in per_class if name not in index
|
||||
}
|
||||
if unknown:
|
||||
raise ValueError(
|
||||
f"--empty-policy 里的类别 {sorted(unknown)} 不在 data.yaml 中;可选 {list(names)}"
|
||||
)
|
||||
|
||||
kept: list[Sample] = []
|
||||
stats: dict[str, tuple[str, int]] = {}
|
||||
for sample in samples:
|
||||
if sample.class_id is not None:
|
||||
kept.append(sample)
|
||||
continue
|
||||
policy = per_class.get(sample.group, default)
|
||||
counted = stats.get(sample.group, (policy, 0))
|
||||
stats[sample.group] = (policy, counted[1] + 1)
|
||||
if policy == "drop":
|
||||
continue
|
||||
if policy == "full":
|
||||
if sample.group not in index:
|
||||
raise ValueError(
|
||||
f"{sample.group!r} 要用整图框,但它不在 data.yaml 的类别里;可选 {list(names)}"
|
||||
)
|
||||
kept.append(sample._replace(full_box=index[sample.group]))
|
||||
else:
|
||||
kept.append(sample)
|
||||
return kept, stats
|
||||
|
||||
|
||||
def main() -> int:
|
||||
@@ -109,8 +206,13 @@ def main() -> int:
|
||||
parser.add_argument("--val-ratio", type=float, default=0.2)
|
||||
parser.add_argument("--seed", type=int, default=42)
|
||||
parser.add_argument(
|
||||
"--drop-empty", action="store_true",
|
||||
help="丢弃没有框的图。默认保留——YOLO 训练里它们是负样本,有助于压低误检",
|
||||
"--empty-policy", nargs="*", default=[], metavar="POLICY|类别=POLICY",
|
||||
help=(
|
||||
"怎么处置没有框的图(标签为空)。可写一个全局默认,再按类别覆盖,如 "
|
||||
"`--empty-policy drop normal=keep black=full`。"
|
||||
"keep=当负样本保留(默认)、drop=丢弃、full=退化成整图框。"
|
||||
"注意空标签在 YOLO 里的意思是『此图无缺陷』,缺陷类的空标签照搬会教模型抑制真实缺陷"
|
||||
),
|
||||
)
|
||||
parser.add_argument("--overwrite", action="store_true", help="输出目录已存在时先清空")
|
||||
parser.add_argument("--dry-run", action="store_true", help="只打印计划")
|
||||
@@ -121,7 +223,7 @@ def main() -> int:
|
||||
logger = setup_logging()
|
||||
|
||||
try:
|
||||
pairs = collect(source)
|
||||
samples = collect(source)
|
||||
except (FileNotFoundError, ValueError) as exc:
|
||||
logger.error("%s", exc)
|
||||
return 1
|
||||
@@ -133,18 +235,37 @@ def main() -> int:
|
||||
meta = yaml.safe_load(meta_path.read_text(encoding="utf-8"))
|
||||
names = [meta["names"][i] for i in sorted(meta["names"])]
|
||||
|
||||
empty = [p for p in pairs if p[2] is None]
|
||||
if args.drop_empty:
|
||||
pairs = [p for p in pairs if p[2] is not None]
|
||||
logger.info("来源: %s(%d 张,%d 类)", source, len(pairs), len(names))
|
||||
logger.info(
|
||||
"无框图片 %d 张:%s", len(empty), "已丢弃" if args.drop_empty else "保留为负样本"
|
||||
logger.info("来源: %s(%d 张,%d 类)", source, len(samples), len(names))
|
||||
try:
|
||||
default_policy, per_class_policy = parse_empty_policy(args.empty_policy)
|
||||
samples, empty_stats = apply_empty_policy(samples, default_policy, per_class_policy, names)
|
||||
except ValueError as exc:
|
||||
logger.error("%s", exc)
|
||||
return 1
|
||||
|
||||
total_empty = sum(count for _, count in empty_stats.values())
|
||||
if total_empty:
|
||||
logger.info("无框图片 %d 张,按来源类别处置:", total_empty)
|
||||
for group, (policy, count) in sorted(empty_stats.items(), key=lambda kv: -kv[1][1]):
|
||||
logger.info(" %-14s %5d 张 -> %s", group or "(顶层)", count, EMPTY_POLICY_DESC[policy])
|
||||
# 只对"默认落到 keep"的类别告警——显式写了 `类别=keep` 的是用户的判断,不再唠叨
|
||||
as_negative = sorted(
|
||||
g for g, (policy, _) in empty_stats.items()
|
||||
if policy == "keep" and g not in per_class_policy
|
||||
)
|
||||
if as_negative:
|
||||
logger.warning(
|
||||
"以上 %s 的空标签会以『此图无缺陷』的身份进入训练。"
|
||||
"如果其中某些类其实是有缺陷、只是没能定位出来,它们会教模型抑制真实缺陷——"
|
||||
"用 --empty-policy 逐类改成 drop 或 full。",
|
||||
"/".join(as_negative),
|
||||
)
|
||||
|
||||
# 按类别分层切分;无框的图单独作为一组分配,避免它们全落进同一侧
|
||||
grouped: dict[int | None, list] = defaultdict(list)
|
||||
for pair in pairs:
|
||||
grouped[pair[2]].append(pair)
|
||||
grouped: dict[int | None, list[Sample]] = defaultdict(list)
|
||||
for sample in samples:
|
||||
# 退化成整图框的那些已经有了确定类别,跟着本类一起分层
|
||||
grouped[sample.full_box if sample.class_id is None else sample.class_id].append(sample)
|
||||
|
||||
rng = random.Random(args.seed)
|
||||
splits: dict[str, list] = {"train": [], "val": []}
|
||||
@@ -156,7 +277,12 @@ def main() -> int:
|
||||
splits["train"].extend(order[n_val:])
|
||||
|
||||
counts = {
|
||||
split: Counter(names[c] if c is not None else "(无框)" for _, _, c in items)
|
||||
split: Counter(
|
||||
names[s.class_id] if s.class_id is not None
|
||||
else names[s.full_box] if s.full_box is not None
|
||||
else "(无框)"
|
||||
for s in items
|
||||
)
|
||||
for split, items in splits.items()
|
||||
}
|
||||
logger.info("划分: train %d / val %d", len(splits["train"]), len(splits["val"]))
|
||||
@@ -178,7 +304,8 @@ def main() -> int:
|
||||
modes: Counter[str] = Counter()
|
||||
seen: dict[str, Path] = {}
|
||||
for split, items in splits.items():
|
||||
for image, label, _ in items:
|
||||
for sample in items:
|
||||
image = sample.image
|
||||
# 拍平之后不同类别目录下的同名文件会撞车,显式挡住
|
||||
if image.name in seen:
|
||||
logger.error(
|
||||
@@ -189,7 +316,13 @@ def main() -> int:
|
||||
return 1
|
||||
seen[image.name] = image
|
||||
modes[link_or_copy(image, out_dir / "images" / split / image.name)] += 1
|
||||
link_or_copy(label, out_dir / "labels" / split / f"{image.stem}.txt")
|
||||
destination = out_dir / "labels" / split / f"{image.stem}.txt"
|
||||
if sample.full_box is None:
|
||||
link_or_copy(sample.label, destination)
|
||||
else:
|
||||
# 整图框:内容与源标签不同,只能新写一份,不能链接
|
||||
destination.parent.mkdir(parents=True, exist_ok=True)
|
||||
destination.write_text(f"{sample.full_box} 0.5 0.5 1.0 1.0\n", encoding="utf-8")
|
||||
|
||||
write_data_yaml(out_dir / "data.yaml", names, root=out_dir.resolve(),
|
||||
train="images/train", val="images/val")
|
||||
@@ -197,9 +330,12 @@ def main() -> int:
|
||||
json.dumps(
|
||||
{
|
||||
"source": str(source.resolve()),
|
||||
"num_images": len(pairs),
|
||||
"empty_labels": len(empty),
|
||||
"dropped_empty": args.drop_empty,
|
||||
"num_images": len(samples),
|
||||
"empty_labels": {
|
||||
group: {"policy": policy, "count": count}
|
||||
for group, (policy, count) in sorted(empty_stats.items())
|
||||
},
|
||||
"empty_policy": {"default": default_policy, **per_class_policy},
|
||||
"val_ratio": args.val_ratio,
|
||||
"seed": args.seed,
|
||||
"split_sizes": {k: len(v) for k, v in splits.items()},
|
||||
|
||||
@@ -91,13 +91,60 @@ def test_empty_labels_kept_as_negatives_by_default(source, tmp_path):
|
||||
out = tmp_path / "data" / "boxes"
|
||||
assert run(source, out) == 0
|
||||
summary = json.loads((out / "summary.json").read_text(encoding="utf-8"))
|
||||
assert summary["empty_labels"] == 1
|
||||
assert summary["empty_labels"] == {"normal": {"policy": "keep", "count": 1}}
|
||||
assert summary["num_images"] == 13
|
||||
|
||||
out_dropped = tmp_path / "data" / "dropped"
|
||||
assert run(source, out_dropped, "--drop-empty") == 0
|
||||
dropped = json.loads((out_dropped / "summary.json").read_text(encoding="utf-8"))
|
||||
assert dropped["num_images"] == 12
|
||||
|
||||
def test_empty_policy_drop_removes_the_image(source, tmp_path):
|
||||
out = tmp_path / "data" / "boxes"
|
||||
assert run(source, out, "--empty-policy", "drop") == 0
|
||||
summary = json.loads((out / "summary.json").read_text(encoding="utf-8"))
|
||||
assert summary["num_images"] == 12
|
||||
assert summary["empty_labels"]["normal"]["policy"] == "drop"
|
||||
assert not (out / "labels" / "train" / "normal_0.txt").exists()
|
||||
assert not (out / "images" / "train" / "normal_0.png").exists()
|
||||
|
||||
|
||||
def test_empty_policy_is_per_class(source, tmp_path):
|
||||
"""缺陷类的空标签丢掉,normal 的留作负样本——两种处置能共存。"""
|
||||
out = tmp_path / "data" / "boxes"
|
||||
assert run(source, out, "--empty-policy", "drop", "normal=keep") == 0
|
||||
summary = json.loads((out / "summary.json").read_text(encoding="utf-8"))
|
||||
assert summary["empty_labels"]["normal"]["policy"] == "keep"
|
||||
assert summary["num_images"] == 13
|
||||
|
||||
|
||||
def test_empty_policy_full_writes_a_whole_image_box(source, tmp_path):
|
||||
"""整图属性的类别退化成整图框:标签要重写,不能链接源文件(内容不同)。"""
|
||||
out = tmp_path / "data" / "boxes"
|
||||
assert run(source, out, "--empty-policy", "normal=full") == 0
|
||||
|
||||
label = next(
|
||||
p for split in ("train", "val")
|
||||
for p in (out / "labels" / split).iterdir()
|
||||
if p.stem == "normal_0"
|
||||
)
|
||||
assert label.read_text(encoding="utf-8").split() == ["1", "0.5", "0.5", "1.0", "1.0"]
|
||||
# 重写而不是硬链接,源标签必须还是空的
|
||||
assert (source / "labels" / "normal" / "normal_0.txt").read_text(encoding="utf-8") == ""
|
||||
|
||||
# 有了确定类别之后,它要跟着 normal 一起参与分层
|
||||
per_class = json.loads((out / "summary.json").read_text(encoding="utf-8"))["per_class"]
|
||||
assert per_class["train"]["normal"] + per_class["val"]["normal"] == 5
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"tokens,expected",
|
||||
[
|
||||
(["drop", "nromal=keep"], "不在 data.yaml"), # 类别拼错
|
||||
(["normal=kep"], "未知策略"), # 策略拼错
|
||||
(["dorp"], "看不懂"), # 全局默认拼错
|
||||
],
|
||||
)
|
||||
def test_empty_policy_rejects_typos(source, tmp_path, capsys, tokens, expected):
|
||||
"""静默忽略拼错的类别名会让策略看起来生效了、其实没有。"""
|
||||
assert run(source, tmp_path / "out", "--empty-policy", *tokens) != 0
|
||||
assert expected in capsys.readouterr().out
|
||||
|
||||
|
||||
def test_data_yaml_uses_absolute_path_and_source_names(source, tmp_path):
|
||||
|
||||
Reference in New Issue
Block a user