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>

tests/test_prepare_yolo_dataset.py

@@ -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):