feat(detect): --label-studio 一步生成可导入 Label Studio 的复核视图

label-studio-converter import yolo 只认 <input>/{images,labels,classes.txt}，且 os.listdir 不递归，看不见 train/val 子目录，直接喂数据集会 "No labels converted"。按类别重命名后文件名全局唯一，于是在 <out>/label_studio/ 下把两个 split 拍平（硬链接：Label Studio 本地存储会校验路径在 DOCUMENT_ROOT 之下，软链接可能越界），再调用 converter 生成 tasks.json 与 labeling config。 - 框以 predictions 导入：它们是 SHAP/Grad-CAM 生成的，审核员提交后才成为 annotation，导出时没审过的框不会混进去。 - 不传 image_dims：真实数据有 3223 种尺寸，传了会写错每条标注的宽高。 - 任务数与图片数不符时报错，而不是静默少导。 - converter 自带的导入提示漏掉了 LABEL_STUDIO_LOCAL_FILES_* 环境变量（它在循环里改写了 image_root_url，之后与默认值比较失败），静音后由脚本打印带实际路径的步骤。 Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-15 17:06:40 +08:00
parent 7adc5b6332
commit 1a43267b55
3 changed files with 201 additions and 1 deletions
@@ -387,3 +387,75 @@ def test_kept_empty_labels_named_after_source_folder(source, tmp_path):
    assert run(source, out) == 0
    assert output_of(out, "normal_0").stem.startswith("normal_")
    assert len([s for s in _stems(out) if s.startswith("normal_")]) == 5
+
+
+@pytest.fixture
+def label_studio_out(source, tmp_path):
+    pytest.importorskip("label_studio_sdk.converter.imports.yolo")
+    out = tmp_path / "data" / "boxes"
+    assert run(source, out, "--empty-policy", "normal=keep", "--label-studio") == 0
+    return out
+
+
+def _tasks(out):
+    return json.loads((out / "label_studio" / "tasks.json").read_text(encoding="utf-8"))
+
+
+def test_label_studio_view_is_flat_and_hard_linked(label_studio_out):
+    """converter 的 os.listdir 不递归，必须拍平；且与训练集共用 inode，不占磁盘。"""
+    view = label_studio_out / "label_studio"
+    images = sorted(view.glob("images/*.png"))
+    assert len(images) == 13
+    assert not [p for p in (view / "images").iterdir() if p.is_dir()]
+    for image in images:
+        original = next(label_studio_out.glob(f"images/*/{image.name}"))
+        assert image.stat().st_ino == original.stat().st_ino
+    assert (view / "classes.txt").read_text(encoding="utf-8").split() == CLASSES
+
+
+def test_label_studio_tasks_are_predictions_with_urls(label_studio_out):
+    """每张图一个任务；框作为 predictions，图片 URL 相对 DOCUMENT_ROOT。"""
+    tasks = _tasks(label_studio_out)
+    assert len(tasks) == 13
+    for task in tasks:
+        assert "annotations" not in task
+        assert task["data"]["image"].startswith("/data/local-files/?d=images/")
+        name = task["data"]["image"].rsplit("/", 1)[1]
+        assert (label_studio_out / "label_studio" / "images" / name).exists()
+
+
+def test_label_studio_boxes_round_trip_to_yolo(label_studio_out):
+    """Label Studio 的左上角百分比坐标反算回 YOLO 中心点坐标，必须与标签一致。"""
+    view = label_studio_out / "label_studio"
+    checked = 0
+    for task in _tasks(label_studio_out):
+        name = Path(task["data"]["image"].rsplit("/", 1)[1]).stem
+        lines = (view / "labels" / f"{name}.txt").read_text(encoding="utf-8").split()
+        results = task["predictions"][0]["result"]
+        if not lines:
+            assert results == []        # 保留下来的空标签：任务里没有框
+            continue
+        value = results[0]["value"]
+        class_id, cx, cy, w, h = lines
+        assert value["rectanglelabels"] == [CLASSES[int(class_id)]]
+        assert value["x"] / 100 + value["width"] / 200 == pytest.approx(float(cx))
+        assert value["y"] / 100 + value["height"] / 200 == pytest.approx(float(cy))
+        assert value["width"] / 100 == pytest.approx(float(w))
+        checked += 1
+    assert checked == 12
+
+
+def test_label_studio_config_and_summary(label_studio_out):
+    config = (label_studio_out / "label_studio" / "tasks.label_config.xml").read_text(encoding="utf-8")
+    for name in CLASSES:
+        assert f'value="{name}"' in config
+    summary = json.loads((label_studio_out / "summary.json").read_text(encoding="utf-8"))
+    assert summary["label_studio"]["tasks"] == 13
+    assert Path(summary["label_studio"]["document_root"]).is_absolute()
+
+
+def test_label_studio_not_built_by_default(source, tmp_path):
+    out = tmp_path / "data" / "boxes"
+    assert run(source, out) == 0
+    assert not (out / "label_studio").exists()
+    assert json.loads((out / "summary.json").read_text(encoding="utf-8"))["label_studio"] is None