{
  "architecture": "swiftformer_s",
  "num_classes": 3,
  "num_features": 224,
  "global_pool": "avg",
  "pretrained_cfg": {
    "tag": "dist_in1k",
    "custom_load": false,
    "input_size": [
      3,
      224,
      224
    ],
    "fixed_input_size": true,
    "interpolation": "bicubic",
    "crop_pct": 0.95,
    "crop_mode": "center",
    "mean": [
      0.485,
      0.456,
      0.406
    ],
    "std": [
      0.229,
      0.224,
      0.225
    ],
    "num_classes": 1000,
    "label_names": [
      "NSFL",
      "NSFW",
      "SFW"
    ],
    "pool_size": null,
    "first_conv": "stem.0",
    "classifier": [
      "head",
      "head_dist"
    ],
    "license": "apache-2.0",
    "origin_url": "https://github.com/Amshaker/SwiftFormer",
    "paper_name": "SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications",
    "paper_ids": "arXiv:2303.15446"
  }
}