data/dbv4_full_dataset_summary.json

{
  "repo_id": "animetimm/danbooru-wdtagger-v4-w640-ws-full",
  "pretrained_tag": "dbv4-full",
  "source": "Danbooru-derived metadata cleaned by SmilingWolf, as described in the dataset card.",
  "format": "WebDataset",
  "image_rule": "Images are resized so min(width, height) <= 640.",
  "splits": [
    {
      "name": "train",
      "images": 5321713,
      "total_size": "318 GB"
    },
    {
      "name": "test",
      "images": 295926,
      "total_size": "17.7 GB"
    },
    {
      "name": "val",
      "images": 296957,
      "total_size": "17.8 GB"
    }
  ],
  "total_images": 5914596,
  "total_size": "353.5 GB",
  "sample_fields": [
    "webp",
    "json.id",
    "json.width",
    "json.height",
    "json.rating",
    "json.general_tags",
    "json.character_tags"
  ],
  "selected_tags": {
    "total": 12476,
    "general": 9225,
    "character": 3247,
    "rating": 4
  }
}