Buckets:

3.68 TB
11,657,081 files
Updated about 4 hours ago
Name
Size
labels
README.md10.7 kB
xet
README.md

9 µm ink detection labels

Ink labels for training Herculaneum ink-detection models at ~9 µm isotropic resolution, across four scrolls. Labels only - no CT data; surface volumes come from the open-data server. The models trained on these labels live at scrollprize/ink_9um. Training and inference code: villa @ merge-ink-pipelines - see ink-detection/configs/README.md

Layout

ink_9um/
  labels/
    aligned-scrollprizeorg-21slices/    24 segments (PHerc0139, PHerc1667, PHercParis4, PHerc0814)
      <segment>/
        <segment>_inklabels.zarr
        <segment>_supervision_mask.zarr
        <segment>_validation_mask.zarr   (3 segments only)
    native9-scrollprizeorg-21slices/    5 segments (PHerc0139 w035 w039 w040 w041 w044)
      <segment>/
        <segment>_inklabels.zarr
        <segment>_supervision_mask.zarr

Labels

The two folders are two different sources at the same effective scale:

  • aligned-scrollprizeorg-21slices: annotations transferred onto public 2.4 µm surface volumes, then pooled 4x in XYZ to ~9.6 µm. Arrays are 21 slices deep, annotated only at Z=10; the other planes are zero.
  • native9-scrollprizeorg-21slices: annotations made directly on native 9.362 µm PHerc. 0139 volumes. Arrays are 28 slices deep, annotated only at Z=14.

They stay separate because the training configs read them as two datasets entries, each with its own segments_path. Point the entries at the two folders:

"datasets": [
  {
    "segments_path": "/path/to/ink_9um/labels/aligned-scrollprizeorg-21slices",
    ...
  },
  {
    "segments_path": "/path/to/ink_9um/labels/native9-scrollprizeorg-21slices",
    ...
  }
]

The training loader finds <segments_path>/<segment>/<segment>_inklabels.zarr and friends on its own, so the layout here is exactly what a training run consumes. The three _validation_mask.zarr segments (pherc0139-w016, pherc0814-46527, pherc1667-w029) are the online-validation cases the released checkpoints report metrics on

Annotations originate from the Vesuvius Challenge ink annotation dataset and were transferred onto the public surface volumes with the tifxyz_label_transfer scripts in villa (volume-cartographer/scripts/tifxyz_label_transfer), with a per-case offset review

Source volumes

The labels annotate the public z-anisotropic 2.399 µm volumes downsampled to ~9.6 µm isotropic (level-2 XY, 4x z mean-pooling), with segments from PHerc. 0139 (9), Scroll 1667 (6), PHerc. Paris 4 (8), and PHerc. 0814 (1), plus 5 native 9.362 µm segments from PHerc. 0139. See the model README for how inputs are prepared

Aligned public 2.399 µm volumes (used at level-2 XY with 4x z mean-pooling):

Segment Scroll Source volume
pherc0139-w016 PHerc. 0139 20250108000004-w029_2025010827 · 2.399 µm
pherc0139-w017 PHerc. 0139 20250108000005-w030_2025010818 · 2.399 µm
pherc0139-w028 PHerc. 0139 20260115000000-w044_2026011522 · 2.399 µm
pherc0139-w029 PHerc. 0139 20260126000000-w045_2026012619 · 2.399 µm
pherc0139-w035 PHerc. 0139 20260317000000-w035_2026031718 · 2.399 µm
pherc0139-w039 PHerc. 0139 20260302000000-w039_2026030210 · 2.399 µm
pherc0139-w040 PHerc. 0139 20250831000000-w040_2025083102 · 2.399 µm
pherc0139-w041 PHerc. 0139 20260108000000-w041_2026010816 · 2.399 µm
pherc0139-w043 PHerc. 0139 20260112000000-w043_2026011217 · 2.399 µm
pherc0814-46527 PHerc. 0814 20260226000000-46527_2um_try2 · 2.399 µm
pherc1667-w013 Scroll 1667 20240304141531-w013_20240304141531_flatboi · 2.399 µm
pherc1667-w018 Scroll 1667 20240304144031-w018_20240304144031_flatboi · 2.399 µm
pherc1667-w023 Scroll 1667 20240304161941-w023_20240304161941_flatboi · 2.399 µm
pherc1667-w028 Scroll 1667 20251208130119-w028_20251208130119156_flatboi · 2.399 µm
pherc1667-w029 Scroll 1667 20251212185248-w029_20251212185248662_flatboi · 2.399 µm
pherc1667-w031 Scroll 1667 20251223230000-w031_2025122323_flatboi · 2.399 µm
phercparis4-w00 PHerc. Paris 4 20231016151002 · 2.399 µm
phercparis4-w01 PHerc. Paris 4 20230702185753 · 2.399 µm
phercparis4-w02 PHerc. Paris 4 20231031143852 · 2.399 µm
phercparis4-w03 PHerc. Paris 4 20231106155351 · 2.399 µm
phercparis4-w05 PHerc. Paris 4 20231012184424 · 2.399 µm
phercparis4-w06 PHerc. Paris 4 20231210121321 · 2.399 µm
phercparis4-w07 PHerc. Paris 4 20231007101619 · 2.399 µm
phercparis4-w09 PHerc. Paris 4 20230929220926 · 2.399 µm

Native 9.362 µm volumes (PHerc. 0139, used as-is):

Note: segment names in the first column come from the annotation dataset and do not track the public segment w-numbering - e.g. pherc0139-w016 maps to the public segment 20250108000004-w029

Total size
3.68 TB
Files
11,657,081
Last updated
Aug 18
Pre-warmed CDN
US EU US EU

Contributors