deepinsight/insightface · error · ValueError

1:N evaluation requires at least one gallery image.

Error message

1:N evaluation requires at least one gallery image.

What it means

Raised by run_identity_identification_evaluation when, after collecting the dataset (auto-split or structured), zero gallery images were found. The gallery is the enrolled identity set that probes are matched against, so 1:N evaluation cannot proceed.

Source

Thrown at python-package/insightface/gui/core/evaluation.py:838

def run_identity_identification_evaluation(
    dataset_root: str | Path,
    engine: FaceEngine,
    auto_split: bool = False,
    multi_face_policy: str = MULTI_FACE_REQUIRE_ONE,
    license_status: str = DEFAULT_LICENSE_STATUS,
    progress_callback=None,
    cancel_callback=None,
) -> EvaluationResult:
    root = Path(dataset_root).expanduser()
    if not root.is_dir():
        raise ValueError(f"Dataset root not found: {root}")
    gallery_items, probe_items, unknown_items = (
        _collect_gallery_probe_auto_split(root) if auto_split else _collect_gallery_probe_structured(root)
    )
    if not gallery_items:
        raise ValueError("1:N evaluation requires at least one gallery image.")
    if not probe_items:
        raise ValueError("1:N evaluation requires at least one known probe image.")

    errors: List[Dict[str, Any]] = []
    cache: Dict[str, np.ndarray] = {}
    gallery: List[Dict[str, Any]] = []
    start_all = time.perf_counter()
    for index, item in enumerate(gallery_items):
        embedding = _embedding_for_image(
            Path(item["path"]),
            engine,
            cache,
            errors,
            "gallery",
            multi_face_policy=multi_face_policy,
        )
        if embedding is not None:
            gallery.append({"identity": item["identity"], "path": str(item["path"]), "embedding": embedding})

View on GitHub (pinned to 7fadd420c2)

Solutions

1. Verify gallery folders contain image files with recognized extensions (jpg/png/bmp per list_images)
2. Check recursive listing actually finds images (nested subfolders vs non-recursive expectations)
3. Confirm dataset_root/layout matches the mode (auto_split vs structured)
4. Run a quick count: sum(1 for _ in (root/'gallery').rglob('*') if _.suffix.lower() in {'.jpg','.jpeg','.png','.bmp'})

Example fix

# before
result = run_identity_identification_evaluation(root, auto_split=False)
# after
gallery_imgs = list((root / "gallery").rglob("*.jpg"))
assert gallery_imgs, "no gallery images found"
result = run_identity_identification_evaluation(root, auto_split=False)

from pathlib import Path
EXTS = {".jpg", ".jpeg", ".png", ".bmp"}
gallery_dir = Path(root) / "gallery"
n = sum(1 for f in gallery_dir.rglob("*") if f.suffix.lower() in EXTS)
assert n > 0, "gallery empty"

try:
    result = run_identity_identification_evaluation(root, auto_split=False)
except ValueError as e:
    if "at least one gallery image" in str(e):
        populate_gallery_or_switch_layout()

When it happens

Trigger: Structured mode: gallery/ missing (also caught earlier) or containing no images in any identity folder. Auto-split mode: identity folders exist but contain no readable images, or layout has no recognizable identity folders for gallery assignment.

Common situations: Empty gallery folder or images with unsupported extensions filtered by list_images; dataset_root pointed at probe-only tree; all gallery images dropped by earlier validation.

Related errors

• 1:N evaluation requires at least one known probe image.
• No verification pairs could be generated from the selected i
• 1:N without Auto Split requires gallery/ and probe/ folders.
• Dataset root not found: {root}
• No gallery embeddings could be extracted.

AI-assisted analysis of deepinsight/insightface@7fadd420c2 (2026-08-28). Data as JSON: /api/errors/75375f433a9a55ee. Report an issue: GitHub.