{
  "image_size": 448,
  "patch_size": 16,
  "num_channels": 3,
  "color_order": "RGB",
  "resize_mode": "letterbox",
  "pad_color_rgb": [
    114,
    114,
    114
  ],
  "normalize_mean": [
    0.5,
    0.5,
    0.5
  ],
  "normalize_std": [
    0.5,
    0.5,
    0.5
  ],
  "input_dtype": "float32",
  "input_layout": "BCHW",
  "padding_mask": {
    "required_for_pytorch_forward": true,
    "shape": "(B, H, W)",
    "dtype": "bool",
    "convention": "True = padded pixel, False = valid pixel",
    "all_false_equivalent_to": "no masking"
  },
  "output": {
    "name": "tag_logits",
    "shape": "(B, 19294)",
    "activation": "apply sigmoid for probabilities"
  },
  "notes": [
    "Letterbox resize keeps aspect ratio; pad with the RGB color above to reach 448x448.",
    "Normalize per-channel: (x/255 - mean) / std after letterboxing.",
    "Built-in recommended thresholds are in pr_thresholds.json (per-tag and global)."
  ]
}