{
  "version": "v0.3.0",
  "task": "multi-label image attributes",
  "group": "content",
  "labels": [
    "people",
    "animals",
    "nature",
    "landscape",
    "buildings",
    "vehicles",
    "food",
    "text",
    "handwriting",
    "chart",
    "diagram",
    "table",
    "map",
    "logo-icon",
    "formula",
    "screen",
    "artwork",
    "instruments",
    "furniture",
    "aerial"
  ],
  "names": [
    "People",
    "Animals",
    "Plants",
    "Landscape",
    "Buildings / structures",
    "Vehicles",
    "Food",
    "Text",
    "Handwriting",
    "Chart",
    "Diagram",
    "Table",
    "Map",
    "Logo / icon",
    "Formula",
    "Screen / UI",
    "Artwork",
    "Instruments",
    "Furniture",
    "Aerial"
  ],
  "definitions": {
    "people": "one or more humans, or clearly human faces, hands or bodies",
    "animals": "animals, birds, fish or insects",
    "nature": "living green things: trees, plants, flowers, crops; not grass or a lawn as ground, not sea, sky or rocks (those are Landscape)",
    "landscape": "an outdoor view of land, sea, sky, mountains, rocks, rivers or a city as a whole",
    "buildings": "buildings, interiors where the room or its architecture is clearly visible, and other built structures: bridges, towers, dams, monuments, ruins",
    "vehicles": "cars, bikes, trains, ships, planes or other vehicles",
    "food": "food or drinks",
    "text": "running text, sentences, lists or a page that make up a substantial part of the image; labels, captions, titles and signs don't count",
    "handwriting": "handwritten text, notes or signatures",
    "chart": "a data plot: values on axes or as proportions (bar, line, pie, scatter, area chart or similar)",
    "diagram": "structure or relationships without measured values: a flowchart, schematic, process or relationship diagram; also labelled drawings that show how something is built (anatomy, parts, cross-sections)",
    "table": "text or numbers laid out in rows and columns, with or without grid lines; not the furniture",
    "map": "a geographic map, floor plan or route map",
    "logo-icon": "a logo, icon, emblem, badge or pictogram",
    "formula": "mathematical, chemical or other notation",
    "screen": "an app, website or device interface",
    "artwork": "made as art: a painting, illustration, cartoon or sculpture, as the image itself or shown in it; not drawings made to explain (those are Diagram)",
    "instruments": "musical instruments: guitar, piano, violin, drums, wind instruments and the like",
    "furniture": "chairs, tables, beds, sofas, desks, cabinets, shelves and other furniture (a data table is Table)",
    "aerial": "the ground seen from high above: aerial or satellite photos, drone shots, bird's-eye views, also through a plane window, straight down or at an angle; clouds without ground don't count; a drawn map is Map"
  },
  "thresholds": {
    "people": 0.7144,
    "animals": 0.1187,
    "nature": 0.3883,
    "landscape": 0.7706,
    "buildings": 0.3697,
    "vehicles": 0.4221,
    "food": 0.9254,
    "text": 0.5949,
    "handwriting": 0.5921,
    "chart": 0.4514,
    "diagram": 0.891,
    "table": 0.802,
    "map": 0.8648,
    "logo-icon": 0.3627,
    "formula": 0.3419,
    "screen": 0.791,
    "artwork": 0.076,
    "instruments": 0.9507,
    "furniture": 0.5897,
    "aerial": 0.1135
  },
  "input": {
    "name": "pixel_values",
    "shape": [
      "batch",
      3,
      224,
      224
    ],
    "mean": [
      0.485,
      0.456,
      0.406
    ],
    "std": [
      0.229,
      0.224,
      0.225
    ],
    "preprocessing": "RGB; resize to img_size x img_size (bilinear, antialiased, no crop, aspect not preserved); scale to [0,1]; (x - mean) / std; NCHW float32"
  },
  "output": {
    "name": "logits",
    "activation": "sigmoid per label; present when >= its threshold"
  },
  "backbone": "efficientnet_b0.ra_in1k"
}